© 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. 0-CLT-HP
    4. 90997
    Prev
    Next
    INDEX
    Explanations

    attention

    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
     attention
    -2.11
    attention
    -1.76
     Attention
    -1.63
    Attention
    -1.45
     attentions
    -1.34
     ATTENTION
    -1.34
    attenzione
    -1.20
     aandacht
    -1.16
     Aufmerksamkeit
    -1.16
     attenzione
    -1.13
    POSITIVE LOGITS
     to
    0.74
    .
    0.52
    minecraftforge
    0.52
    addGap
    0.50
    lösung
    0.50
     of
    0.47
     that
    0.46
     vía
    0.46
     for
    0.45
    Agriculture
    0.44
    Activations Density 0.090%

    No Known Activations