© 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. 43356
    Prev
    Next
    INDEX
    Explanations

    marin

    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
    ubu
    -1.63
    marin
    -0.92
    </i>
    -0.91
     Réponses
    -0.77
    MLLoader
    -0.77
    kenstock
    -0.75
    ArgsConstructor
    -0.73
    contentLoaded
    -0.72
    RegressionTest
    -0.69
    исленность
    -0.68
    POSITIVE LOGITS
     kiin
    0.47
    <em>
    0.45
     Dop
    0.45
     Mist
    0.45
     preſent
    0.44
    .
    0.44
     pire
    0.43
    entro
    0.43
     Tyl
    0.42
    ers
    0.41
    Activations Density 1.604%

    No Known Activations