© 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. 42488
    Prev
    Next
    INDEX
    Explanations

    health risks and safety

    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
     pleaſure
    -0.79
     Shakspeare
    -0.79
     houſe
    -0.77
     ſtate
    -0.73
     vectorielles
    -0.71
     Shaksp
    -0.71
     Hogarth
    -0.71
     purpoſe
    -0.70
     Longman
    -0.68
     Efq
    -0.67
    POSITIVE LOGITS
    Rüyada
    0.58
     sel
    0.55
    parseFrom
    0.53
     aut
    0.52
    SourceChecksum
    0.52
    +:+
    0.51
    fattning
    0.51
     ProtoMessage
    0.50
    Tils
    0.49
     li
    0.49
    Activations Density 0.109%

    No Known Activations