© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75459
    Prev
    Next
    INDEX
    Explanations

    molds

    np_max-act-logits · 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
     tâm
    -0.51
    sius
    -0.50
    alous
    -0.49
    ≦)
    -0.49
    iettivo
    -0.49
    devamını
    -0.48
    HRC
    -0.47
    soever
    -0.47
    needle
    -0.47
    SCRIBE
    -0.46
    POSITIVE LOGITS
    MigrationBuilder
    0.91
     resourceCulture
    0.81
     esternos
    0.70
     ErrIntOverflow
    0.68
     estekak
    0.66
    ConstraintMaker
    0.66
    contentLoaded
    0.65
     متعلقه
    0.60
     Vikipedi
    0.57
    OGND
    0.56
    Activations Density 0.001%

    No Known Activations