© 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. 5-CLT-HP
    7. 2102
    Prev
    Next
    INDEX
    Explanations

    but

    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
    KommentareTeilen
    -0.65
    SharedDtor
    -0.63
     estekak
    -0.62
    CodeAttribute
    -0.61
    contentLoaded
    -0.60
     Meksiku
    -0.59
    âce
    -0.59
     beginnetje
    -0.56
     Autorizaciones
    -0.55
     للاسماء
    -0.53
    POSITIVE LOGITS
     instead
    0.63
     malah
    0.59
     actually
    0.59
    zungen
    0.55
     indications
    0.54
     virke
    0.53
     actual
    0.53
     unexpected
    0.51
    暂无
    0.51
     DialogInterface
    0.51
    Activations Density 0.006%

    No Known Activations