© 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. 95039
    Prev
    Next
    INDEX
    Explanations

    sic

    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
     the
    -0.71
     our
    -0.61
     Efq
    -0.60
     this
    -0.60
     ainfi
    -0.60
     comparing
    -0.56
     whoſe
    -0.55
     their
    -0.54
     gefällt
    -0.54
    onomian
    -0.54
    POSITIVE LOGITS
    ViewFeatures
    0.68
    Autoritní
    0.66
     ExecuteAsync
    0.59
     виправивши
    0.56
     nakalista
    0.54
    Referanser
    0.52
    Hentet
    0.52
    >",
    0.51
    ly
    0.51
    —
    0.50
    Activations Density 0.002%

    No Known Activations