© 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. 20-CLT-HP
    7. 72962
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act-logits · 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
     henvisninger
    -0.47
     nakalista
    -0.43
    useEffect
    -0.43
    ControllerAdvice
    -0.41
    styleUrls
    -0.41
     Waray
    -0.40
     gyhoeddwyd
    -0.40
    enumi
    -0.40
    tvguidetime
    -0.39
    BeginContext
    -0.39
    POSITIVE LOGITS
    MLLoader
    0.90
    RTEX
    0.73
    Saluti
    0.68
     ويكيميديا
    0.68
     Close
    0.68
     CLOSE
    0.67
    CLOSE
    0.66
     Lightboxes
    0.66
    EndContext
    0.65
     close
    0.64
    Activations Density 0.000%

    No Known Activations