© 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. 94117
    Prev
    Next
    INDEX
    Explanations

    bleeding or breakage

    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
     Accumulation
    -0.54
     accumulation
    -0.54
    srs
    -0.53
     تضيفلها
    -0.52
     bleeding
    -0.48
    TAINMENT
    -0.48
     cosa
    -0.46
    accumulation
    -0.46
     transferir
    -0.46
     kaynağından
    -0.46
    POSITIVE LOGITS
    <bos>
    1.02
     ་་
    0.75
     ſind
    0.71
     houſe
    0.71
    ResponseWriter
    0.70
    httphttps
    0.69
    клопе
    0.69
     Houſe
    0.68
     pleaſure
    0.68
     Anſ
    0.68
    Activations Density 1.485%

    No Known Activations