© 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. 10291
    Prev
    Next
    INDEX
    Explanations

    computer

    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
    yntaxException
    -0.96
     виправивши
    -0.91
    RenderAtEndOf
    -0.88
    CloseOperation
    -0.82
     صوتيه
    -0.82
    uxxxx
    -0.81
     itſelf
    -0.80
     computer
    -0.79
    PyExc
    -0.79
     للمعارف
    -0.78
    POSITIVE LOGITS
    mence
    0.43
     tension
    0.42
    اق
    0.40
    б
    0.40
     gug
    0.39
     pag
    0.38
    hibi
    0.36
     bidding
    0.35
    obach
    0.35
    aliyun
    0.35
    Activations Density 0.026%

    No Known Activations