© 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. Gemma-2-2B
    5. 1-CLT-HP
    7. 512
    Prev
    Next
    INDEX
    Explanations

    alternatives or comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    -0.66
     lenker
    -0.63
    less
    -0.56
    ings
    -0.49
    ans
    -0.49
    ens
    -0.48
    let
    -0.47
    ingly
    -0.47
    oles
    -0.46
    lets
    -0.45
    POSITIVE LOGITS
    \{\\
    0.77
    }{*}{
    0.77
    
    0.74
     الحره
    0.72
    </tfoot>
    0.69
    findpost
    0.68
    AndEndTag
    0.68
    UNIFIED
    0.65
    )();
    0.63
    曖昧さ回避
    0.63
    Activations Density 1.599%

    No Known Activations