© 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. 4-CLT-HP
    7. 4420
    Prev
    Next
    INDEX
    Explanations

    commas

    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
     and
    -0.77
     Yet
    -0.68
    Yet
    -0.62
    новниш
    -0.59
     käytet
    -0.59
     miał
    -0.58
     createSprite
    -0.57
    Abitanti
    -0.57
     Etc
    -0.57
     sanoo
    -0.56
    POSITIVE LOGITS
     the
    0.55
    paya
    0.52
     betweenstory
    0.49
    wapV
    0.49
     IndexPath
    0.47
    //
    0.44
     Harrell
    0.44
     lachen
    0.44
     sapon
    0.42
    #+#
    0.42
    Activations Density 0.002%

    No Known Activations