© 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. 1-CLT-HP
    7. 14663
    Prev
    Next
    INDEX
    Explanations

    vis

    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
    ഏ
    -0.39
    Parcelize
    -0.37
    Whoosh
    -0.36
    -
    -0.36
     gond
    -0.36
    bondale
    -0.35
    stern
    -0.35
    hamilan
    -0.34
    fi
    -0.34
    ts
    -0.34
    POSITIVE LOGITS
    RenderAtEndOf
    0.79
    +:+
    0.74
     ExecuteAsync
    0.73
     بيها
    0.73
    PhysRevLett
    0.71
    httphttps
    0.71
    
    0.71
     архивлан
    0.71
    twimg
    0.70
    VersionUID
    0.68
    Activations Density 0.021%

    No Known Activations