© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1419
    Prev
    Next
    INDEX
    Explanations

    encoding/cutting strings

    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
     ensuing
    -0.84
     intervening
    -0.84
     MainAxisSize
    -0.82
    WebVitals
    -0.82
     للمعارف
    -0.77
    IsContent
    -0.74
    enderror
    -0.73
    XmlAccessorType
    -0.72
    tagHelperRunner
    -0.69
     compound
    -0.69
    POSITIVE LOGITS
     veux
    0.45
    Ur
    0.44
     lager
    0.43
     tomates
    0.41
    tribune
    0.40
     cias
    0.40
    IsRequired
    0.40
    LookAnd
    0.40
    Z
    0.40
     Willen
    0.39
    Activations Density 0.013%

    No Known Activations