© 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. 1-CLT-HP
    7. 9639
    Prev
    Next
    INDEX
    Explanations

    effects

    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
     متعلقه
    -0.70
    TypedDataSet
    -0.70
    bootstrapcdn
    -0.67
    ValueGenerated
    -0.65
    //
    -0.65
    Odkazy
    -0.64
    scriptcase
    -0.63
    قایناق‌لار
    -0.59
    makeConstraints
    -0.58
    Diweddarwch
    -0.57
    POSITIVE LOGITS
     BSD
    0.54
    ὶ
    0.51
    ly
    0.51
    er
    0.50
    oa̍t
    0.49
    ględ
    0.49
    erent
    0.48
     position
    0.48
    vertisers
    0.47
    Apis
    0.47
    Activations Density 0.003%

    No Known Activations