© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43063
    Prev
    Next
    INDEX
    Explanations

    answers, rules

    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>
    -0.66
    ings
    -0.54
    RenderAtEndOf
    -0.52
    ↵↵
    -0.50
    Explanation
    -0.50
    ess
    -0.48
    x
    -0.47
    te
    -0.46
    orm
    -0.46
    end
    -0.46
    POSITIVE LOGITS
     صوتيه
    0.73
    +#+
    0.73
    couples
    0.66
    ratulations
    0.65
     ISNI
    0.65
    )':
    0.62
     חיצוניים
    0.61
    Cliquez
    0.61
     odkazy
    0.60
    fromnode
    0.60
    Activations Density 0.029%

    No Known Activations