© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 95083
    Prev
    Next
    INDEX
    Explanations

    for

    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
    PhysRevD
    -0.57
    iest
    -0.47
     hiring
    -0.47
    ("${
    -0.45
    '][]
    -0.44
     and
    -0.44
     calling
    -0.44
    </s>
    -0.44
    fortawesome
    -0.43
     "#
    -0.43
    POSITIVE LOGITS
    rungsseite
    0.76
     autorytatywna
    0.74
    脚注の使い方
    0.73
     الحره
    0.71
     للاسماء
    0.69
    مصادر
    0.63
     Bäume
    0.63
     estekak
    0.61
    точници
    0.60
    )_/¯
    0.60
    Activations Density 0.001%

    No Known Activations