© 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. 39778
    Prev
    Next
    INDEX
    Explanations

    code

    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
    gyp
    -0.86
     kasarigan
    -0.76
     Himo
    -0.75
     Roskov
    -0.64
    ГЛА
    -0.63
     Meksiku
    -0.58
     phu
    -0.56
     بث
    -0.56
    TagHelpers
    -0.55
    ByExample
    -0.55
    POSITIVE LOGITS
    ברס
    0.54
    утбо
    0.51
     núcleo
    0.51
    Madness
    0.45
    jacent
    0.45
     vicinity
    0.45
     låg
    0.45
    tij
    0.44
     shallo
    0.44
     neighborhoods
    0.44
    Activations Density 0.175%

    No Known Activations