© 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. 4-CLT-HP
    7. 328
    Prev
    Next
    INDEX
    Explanations

    Code, technical, and legal writing

    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
     المعيارى
    -0.68
     فريبيس
    -0.65
    ']>;
    -0.60
    SharedCtor
    -0.59
    WebElementEntity
    -0.58
    CloseOperation
    -0.56
    IDENTAL
    -0.56
    LookAnd
    -0.56
    SourceChecksum
    -0.56
    aska
    -0.55
    POSITIVE LOGITS
     Pingback
    0.54
     InputDecoration
    0.50
    fers
    0.48
     BitSet
    0.48
     NUKAT
    0.45
    aliers
    0.43
    blind
    0.42
    ől
    0.42
    ärs
    0.42
    orra
    0.42
    Activations Density 0.001%

    No Known Activations