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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 821
    Prev
    Next
    INDEX
    Explanations

    negative or concerning terms related to situations or events

    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
    468
    +0.15
    0.4%
    1870
    +0.09
    0.3%
    1056
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.15
    0.07
    1056
    +0.09
    0.06
    2030
    +0.09
    0.04
    Negative Logits
     vœux
    -0.68
    .*")]
    -0.64
     impegno
    -0.57
     preuves
    -0.57
     nouveautés
    -0.54
    HttpDelete
    -0.54
     débats
    -0.54
     féd
    -0.53
    ])*
    -0.52
    OGND
    -0.51
    POSITIVE LOGITS
     monaster
    0.83
    postolic
    0.78
    nachron
    0.77
     tramont
    0.76
     cristi
    0.71
     paff
    0.69
     sement
    0.69
     reputa
    0.69
     vecchi
    0.62
     ideolog
    0.62
    Activations Density 0.264%

    No Known Activations