© 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. 4-CLT-HP
    7. 452
    Prev
    Next
    INDEX
    Explanations

    with

    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
    undred
    -0.53
    ToTop
    -0.48
    gemeester
    -0.48
    onium
    -0.46
    igne
    -0.45
     glove
    -0.45
     condensation
    -0.44
    demi
    -0.44
    ipot
    -0.42
    hon
    -0.42
    POSITIVE LOGITS
    <bos>
    1.46
    OGND
    0.82
    #
    0.77
    ImageContext
    0.66
    ThroughAttribute
    0.62
    '));
    0.60
    IUrlHelper
    0.60
    RenderAtEndOf
    0.59
    InjectAttribute
    0.58
     ModelExpression
    0.58
    Activations Density 0.017%

    No Known Activations