© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14204
    Prev
    Next
    INDEX
    Explanations

    goblins

    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
     Harmful
    -0.70
    Harmful
    -0.67
    exels
    -0.45
    itals
    -0.43
     trattano
    -0.41
    celia
    -0.41
    itanie
    -0.38
    ی
    -0.38
    Surviving
    -0.37
    nę
    -0.36
    POSITIVE LOGITS
    Diwedd
    0.78
     EconPapers
    0.72
    aarrggbb
    0.71
    enderror
    0.68
    enumii
    0.64
     дописавши
    0.63
    +#+
    0.62
     nahilalakip
    0.60
    béco
    0.60
     NSCoder
    0.59
    Activations Density 0.016%

    No Known Activations