© 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. 1-CLT-HP
    4. 45547
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    <bos>
    -0.85
    rungsseite
    -0.66
    IsContent
    -0.66
     <<<<<<<<<<<<<<
    -0.62
    dflare
    -0.60
    InjectAttribute
    -0.58
     @"/
    -0.57
    Билгалдахарш
    -0.57
    ClientRect
    -0.55
    <eos>
    -0.55
    POSITIVE LOGITS
    enumi
    0.52
     />';
    0.50
     you
    0.49
     correctes
    0.49
     unstable
    0.47
    you
    0.44
     women
    0.44
     Collecting
    0.42
     we
    0.42
    anglès
    0.42
    Activations Density 0.016%

    No Known Activations