© 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. 4-CLT-HP
    7. 2012
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    Ib
    -0.41
    Referencias
    -0.40
     pres
    -0.40
     Olen
    -0.40
     Winfrey
    -0.40
    liar
    -0.39
    مراجع
    -0.39
     IBA
    -0.39
    devamını
    -0.38
     dars
    -0.38
    POSITIVE LOGITS
     تضيفلها
    0.84
    astify
    0.72
    parsedMessage
    0.71
    PYX
    0.70
     noqa
    0.70
    OGND
    0.65
    MigrationBuilder
    0.65
     OMITBAD
    0.65
    unknownFields
    0.63
    hearts
    0.63
    Activations Density 0.012%

    No Known Activations