© 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. 5-CLT-HP
    7. 96483
    Prev
    Next
    INDEX
    Explanations

    code/mathematical language

    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
     esternos
    -0.54
     gouver
    -0.54
     raya
    -0.50
    ługość
    -0.50
    BatchNorm
    -0.48
    Hozzáférés
    -0.48
    צלחה
    -0.47
    getreten
    -0.46
     TEND
    -0.46
     Buna
    -0.46
    POSITIVE LOGITS
     صوتيه
    0.66
    ConstraintMaker
    0.65
    AutoScaleMode
    0.61
    windowFixed
    0.60
    ks
    0.60
    isks
    0.59
     المعيارى
    0.56
     Szk
    0.54
     MotionEvent
    0.54
    /**
    0.54
    Activations Density 0.001%

    No Known Activations