© 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. 218
    Prev
    Next
    INDEX
    Explanations

    dates and formatting

    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
    Mutagenicity
    -0.48
    Искәрмәләр
    -0.44
    ','.
    -0.44
     oprot
    -0.43
     بخ
    -0.43
    utm
    -0.43
    pso
    -0.41
    elos
    -0.41
    KommentareTeilen
    -0.40
    gestone
    -0.40
    POSITIVE LOGITS
    ConstraintMaker
    0.65
    uxxxx
    0.63
    SharedCtor
    0.60
    verwijspagina
    0.59
    NameInMap
    0.59
    الدراسه
    0.58
     resourceCulture
    0.57
     Waits
    0.57
    prefixer
    0.56
    SequentialGroup
    0.56
    Activations Density 0.001%

    No Known Activations