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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43493
    Prev
    Next
    INDEX
    Explanations

    thin

    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
    dification
    -0.71
    期刊论文
    -0.56
     Bra
    -0.54
    ridae
    -0.54
     Da
    -0.53
     ram
    -0.51
     mow
    -0.51
     standard
    -0.50
     cap
    -0.49
     sem
    -0.48
    POSITIVE LOGITS
    ValueStyle
    0.91
    principalColumn
    0.77
    Hochspringen
    0.76
     auffi
    0.75
     виправивши
    0.75
    UnusedPrivate
    0.73
    aarrggbb
    0.71
     contextLoads
    0.69
     itſelf
    0.67
    الحياه
    0.66
    Activations Density 0.077%

    No Known Activations