© 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. 12165
    Prev
    Next
    INDEX
    Explanations

    phrases related to freedom and liberation

    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
    1181
    +0.08
    0.2%
    124
    +0.07
    0.2%
    426
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1181
    +0.08
    0.04
    1221
    +0.07
    0.02
    100
    +0.06
    0.04
    Negative Logits
    Encyklopedia
    -0.51
    Pozri
    -0.48
    Morphology
    -0.47
    Externé
    -0.47
    Glej
    -0.46
    getMenuInflater
    -0.46
     Morphology
    -0.46
    內容簡介
    -0.45
    IsInitialized
    -0.44
     ingrat
    -0.43
    POSITIVE LOGITS
     santiago
    0.66
     jati
    0.66
     guatemala
    0.64
     mahd
    0.64
    hematical
    0.64
     quoc
    0.64
     susun
    0.63
     muna
    0.63
     barri
    0.61
     monaster
    0.60
    Activations Density 0.307%

    No Known Activations