© 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. 5-CLT-HP
    7. 5192
    Prev
    Next
    INDEX
    Explanations

    code

    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
    LookAnd
    -0.71
     AssemblyProduct
    -0.69
    MigrationBuilder
    -0.63
     Drapeau
    -0.62
    ">//
    -0.60
    memoized
    -0.59
    }}}{\
    -0.59
     الحره
    -0.59
    UrlResolution
    -0.57
    existsSync
    -0.57
    POSITIVE LOGITS
    ica
    0.49
    ics
    0.47
    ICA
    0.44
    aI
    0.42
    Roman
    0.42
     vaginal
    0.41
     IMA
    0.41
     religieuses
    0.41
    исленность
    0.41
    RetentionPolicy
    0.41
    Activations Density 0.015%

    No Known Activations