© 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. 94709
    Prev
    Next
    INDEX
    Explanations

    computer commands/actions

    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
     Савезне
    -0.93
    Vidite
    -0.88
    mybatisplus
    -0.81
    ArgsConstructor
    -0.76
    Whereas
    -0.76
    الحياه
    -0.71
    Chham
    -0.66
    endpush
    -0.66
    Autoritní
    -0.63
    ionario
    -0.61
    POSITIVE LOGITS
    only
    0.50
     pity
    0.48
     SISTEMA
    0.47
     tuyo
    0.47
    Петербург
    0.46
     tooth
    0.45
    Only
    0.45
     unele
    0.44
     Ravel
    0.44
     Observed
    0.44
    Activations Density 1.615%

    No Known Activations