© 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. 1-CLT-HP
    7. 311
    Prev
    Next
    INDEX
    Explanations

    Some

    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
    amaño
    -0.63
    —(
    -0.63
    patience
    -0.58
    Groetjes
    -0.57
    rangea
    -0.57
     CWE
    -0.56
    AutoScale
    -0.55
    insee
    -0.55
    Pozdrawiam
    -0.54
    omeness
    -0.54
    POSITIVE LOGITS
     незавершена
    0.62
     utafitiHapana
    0.57
    ment
    0.57
    way
    0.55
    ways
    0.53
    time
    0.52
    pan
    0.52
    ling
    0.51
    ton
    0.50
    mi
    0.50
    Activations Density 0.023%

    No Known Activations