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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43354
    Prev
    Next
    INDEX
    Explanations

    returns

    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
     returns
    -1.23
     yields
    -1.05
     Returns
    -0.91
    returns
    -0.89
    Returns
    -0.85
     RETURNS
    -0.85
    featureID
    -0.80
    yields
    -0.71
    tagHelperRunner
    -0.68
     Yields
    -0.66
    POSITIVE LOGITS
     endforeach
    0.77
    <bos>
    0.73
     виправивши
    0.59
    ]]
    0.56
    achim
    0.56
    おはようございます
    0.55
    cythe
    0.54
    Portály
    0.54
    ètement
    0.54
    iffance
    0.53
    Activations Density 0.143%

    No Known Activations