© 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. 1-CLT-HP
    7. 10485
    Prev
    Next
    INDEX
    Explanations

    incenti

    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
    Personendaten
    -0.84
    QMetaType
    -0.66
    kloped
    -0.65
     @"/
    -0.60
    tonode
    -0.59
    tagHelperRunner
    -0.59
     &___
    -0.59
     PublicKey
    -0.59
    interopRequire
    -0.59
    abyrinth
    -0.59
    POSITIVE LOGITS
     in
    0.54
    фикации
    0.48
     borsa
    0.44
     boeken
    0.43
     Landschaft
    0.43
     beraber
    0.43
     parlant
    0.43
    fej
    0.43
     dancers
    0.43
     partidas
    0.43
    Activations Density 0.023%

    No Known Activations