Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44885
    Prev
    Next
    INDEX
    Explanations

    to

    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
     you
    -0.73
    hlungen
    -0.60
     them
    -0.57
     your
    -0.56
     its
    -0.53
    pressing
    -0.52
     our
    -0.52
     keting
    -0.52
    throws
    -0.50
     voci
    -0.50
    POSITIVE LOGITS
    <bos>
    0.80
     }}"></
    0.80
    DockStyle
    0.78
    ihnachts
    0.68
    .*")]
    0.67
     never
    0.66
    />";
    0.66
     متعلقه
    0.64
    談社
    0.63
     do
    0.60
    Activations Density 0.107%

    No Known Activations