© 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. 5-CLT-HP
    7. 91742
    Prev
    Next
    INDEX
    Explanations

    wen

    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
    Amicalement
    -0.80
     intptr
    -0.80
    =$?
    -0.73
    "])
    -0.72
    IntoConstraints
    -0.70
    archiviato
    -0.69
    ")));
    -0.69
    addCriterion
    -0.67
    ConstraintMaker
    -0.66
    ----------
    -0.65
    POSITIVE LOGITS
    I
    0.59
    you
    0.56
    <bos>
    0.55
    a
    0.55
    is
    0.54
    i
    0.54
    we
    0.53
    es
    0.52
    it
    0.52
    use
    0.52
    Activations Density 0.000%

    No Known Activations