© 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. 91057
    Prev
    Next
    INDEX
    Explanations

    uneven

    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
    m
    -1.00
    ant
    -0.78
    a
    -0.62
    ss
    -0.59
    aq
    -0.59
    mc
    -0.58
    is
    -0.57
    y
    -0.57
    MC
    -0.56
    ak
    -0.54
    POSITIVE LOGITS
     CreateTagHelper
    0.76
     المعيارى
    0.74
    Przypisy
    0.67
     EconPapers
    0.65
    FunctionFlags
    0.63
    ագրություններ
    0.58
     nakalista
    0.58
    dafx
    0.57
     فريبيس
    0.56
    Literatur
    0.55
    Activations Density 0.150%

    No Known Activations