© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7406
    Prev
    Next
    INDEX
    Explanations

    words related to nudity and undressing, especially in public settings or in front of others

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1385
    +0.11
    0.3%
    1842
    +0.10
    0.3%
    1843
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.11
    0.05
    1984
    +0.10
    0.06
    273
    +0.09
    0.04
    Negative Logits
    dónde
    -0.52
    ovon
    -0.52
    Faktor
    -0.51
    quién
    -0.49
     Kategor
    -0.46
    Зноскі
    -0.46
     propriétaires
    -0.45
    Lato
    -0.44
    enterOuterAlt
    -0.44
    Translations
    -0.43
    POSITIVE LOGITS
     others
    1.15
     Others
    0.93
    others
    0.93
     OTHERS
    0.92
    Others
    0.89
     someone
    0.85
     somebody
    0.82
     fellow
    0.79
    trui
    0.76
     Mejía
    0.75
    Activations Density 0.507%

    No Known Activations