© 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. 1-CLT-HP
    7. 532
    Prev
    Next
    INDEX
    Explanations

    over

    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
     loto
    -0.56
    قایناق‌لار
    -0.56
    Crossref
    -0.54
    GEBURTSDATUM
    -0.51
    SourceChecksum
    -0.51
    Дети
    -0.49
    참고
    -0.48
     Paroles
    -0.48
    ValueStyle
    -0.47
     olympique
    -0.47
    POSITIVE LOGITS
    StructEnd
    0.68
     FetchType
    0.66
    jsii
    0.65
     RequestMethod
    0.54
    >{@
    0.53
    SocketAddress
    0.51
    toHave
    0.49
    aarrggbb
    0.49
     AssemblyCulture
    0.49
     WaitForSeconds
    0.49
    Activations Density 0.015%

    No Known Activations