© 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. 4491
    Prev
    Next
    INDEX
    Explanations

    rockets and government and school

    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
     HasFactory
    -0.74
    addPreferredGap
    -0.74
    GraphicsUnit
    -0.66
    ArgsConstructor
    -0.65
    addGap
    -0.59
    __*/
    -0.58
    XmlAccessorType
    -0.58
    WebElementEntity
    -0.57
    клопе
    -0.57
    ViewById
    -0.57
    POSITIVE LOGITS
    ’
    0.59
     carcass
    0.57
     AssemblyCulture
    0.55
     bells
    0.55
     carcasses
    0.55
     locomotives
    0.53
     adapter
    0.51
    '
    0.50
     adapters
    0.50
     complement
    0.50
    Activations Density 0.000%

    No Known Activations