© 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. 14807
    Prev
    Next
    INDEX
    Explanations

    quotations

    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
     ‘
    -1.16
     ‚
    -0.93
     '
    -0.92
     (‘
    -0.91
     color
    -0.85
     colored
    -0.84
     colors
    -0.83
     flavor
    -0.82
     armor
    -0.82
     jewelry
    -0.81
    POSITIVE LOGITS
    StoryboardSegue
    0.70
     propOrder
    0.69
     صوتيه
    0.60
    awtextra
    0.58
     nahilalakip
    0.57
     AssemblyCulture
    0.56
    basicConfig
    0.56
    InSection
    0.54
    oredCriteria
    0.53
    posh
    0.52
    Activations Density 0.010%

    No Known Activations