© 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. 91846
    Prev
    Next
    INDEX
    Explanations

    Frozen

    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
    లాలు
    -0.53
    UrlResolution
    -0.50
    badi
    -0.49
     partij
    -0.47
    UnknownFieldSet
    -0.46
    口
    -0.46
    Rhestr
    -0.46
    findpost
    -0.46
    ValueGeneration
    -0.45
    ScopeManager
    -0.45
    POSITIVE LOGITS
     solid
    0.91
    solid
    0.77
     shut
    0.77
     sólido
    0.71
    Solid
    0.68
     SOLID
    0.67
     Solid
    0.67
    Portail
    0.65
     solide
    0.65
     solida
    0.64
    Activations Density 0.000%

    No Known Activations