© 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. 0-CLT-HP
    7. 97692
    Prev
    Next
    INDEX
    Explanations

    insurance and probation

    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
    heimer
    -1.46
    orean
    -1.38
     doInBackground
    -0.94
     виправивши
    -0.85
    anthin
    -0.83
    ImageContext
    -0.83
    IntoConstraints
    -0.82
    parsedMessage
    -0.82
    rrggbb
    -0.81
     Roskov
    -0.80
    POSITIVE LOGITS
    <eos>
    0.50
     sẻ
    0.47
    /
    0.46
    ec
    0.45
     is
    0.45
    </strong>
    0.43
    all
    0.43
    roll
    0.42
     @
    0.41
    ā
    0.41
    Activations Density 1.748%

    No Known Activations