© 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. 0-CLT-HP
    7. 93346
    Prev
    Next
    INDEX
    Explanations

    Thread, CNC, and code

    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
    ModelAdmin
    -0.63
     referrerpolicy
    -0.61
    JNIEnv
    -0.61
    wpi
    -0.61
     noexcept
    -0.59
     referenties
    -0.59
     machining
    -0.58
    Thread
    -0.57
    WebVitals
    -0.57
    DoubleQuotes
    -0.56
    POSITIVE LOGITS
    ing
    0.68
    atively
    0.60
    ed
    0.60
    izing
    0.60
    ING
    0.60
    ized
    0.56
    cing
    0.56
    ingly
    0.52
    icked
    0.52
    mű
    0.52
    Activations Density 0.143%

    No Known Activations