© 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. 40107
    Prev
    Next
    INDEX
    Explanations

    {{

    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
     Efq
    -0.78
     ſever
    -0.73
     raiſ
    -0.69
     itſelf
    -0.69
     NSCoder
    -0.66
    NUMX
    -0.65
     myſelf
    -0.65
     himſelf
    -0.64
     Reſ
    -0.63
     صوتيه
    -0.63
    POSITIVE LOGITS
    permalink
    0.52
     she
    0.52
     Worth
    0.50
    amma
    0.49
     виправивши
    0.49
    [:-
    0.46
    oxia
    0.46
     ou
    0.45
     ويكيپيديا
    0.45
    μαστε
    0.44
    Activations Density 0.588%

    No Known Activations