© 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. 94022
    Prev
    Next
    INDEX
    Explanations

    technical documentation

    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
    zuma
    -1.08
    TypedDataSet
    -0.75
    migrationBuilder
    -0.73
    TestingModule
    -0.73
    makeConstraints
    -0.73
    setVerticalGroup
    -0.69
    IntoConstraints
    -0.69
    EndContext
    -0.64
    isation
    -0.63
    pulumi
    -0.62
    POSITIVE LOGITS
    Bissau
    0.57
    Them
    0.51
     Them
    0.49
     souri
    0.48
     separado
    0.47
     decenas
    0.46
    ly
    0.46
    albero
    0.45
     dizaines
    0.45
     hommes
    0.44
    Activations Density 0.146%

    No Known Activations