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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92048
    Prev
    Next
    INDEX
    Explanations

    written communications

    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
     ſeveral
    -0.68
     Efq
    -0.67
     Jefus
    -0.66
    webtoken
    -0.65
     समीक्षाओं
    -0.64
     alſo
    -0.64
    SourceChecksum
    -0.64
    XMLSchema
    -0.63
    intenance
    -0.62
    SharedCtor
    -0.62
    POSITIVE LOGITS
     AssemblyCulture
    0.52
    EndContext
    0.51
     CreateTagHelper
    0.50
    Điều
    0.44
     necessarily
    0.44
     Complexity
    0.43
     kond
    0.43
     corde
    0.43
     say
    0.42
    帖最后由
    0.40
    Activations Density 1.690%

    No Known Activations