© 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. 4441
    Prev
    Next
    INDEX
    Explanations

    is are

    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
     resourceCulture
    -0.67
    extAlignment
    -0.56
    WireFormatLite
    -0.56
    ագրություններ
    -0.52
    LayoutStyle
    -0.51
    ForRow
    -0.49
     surla
    -0.48
    memberOf
    -0.47
     Hongrie
    -0.46
    enapa
    -0.45
    POSITIVE LOGITS
     الاطلاع
    0.73
     amortization
    0.60
     extradition
    0.60
     adsorption
    0.60
     diversification
    0.59
     revocation
    0.59
     élector
    0.59
     urbanization
    0.59
     the
    0.58
     repentance
    0.57
    Activations Density 0.004%

    No Known Activations