© 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. 5-CLT-HP
    7. 3422
    Prev
    Next
    INDEX
    Explanations

    code, numbers, technical details

    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
    
    -0.70
    tonode
    -0.61
    Reentrant
    -0.54
    Попис
    -0.54
    hnia
    -0.54
    abetes
    -0.52
    पया
    -0.52
    ništvo
    -0.51
    sschutz
    -0.51
    __':
    -0.51
    POSITIVE LOGITS
    icksburg
    0.48
     useSelector
    0.47
    nextProps
    0.45
     Horv
    0.44
    əl
    0.44
    VolleyError
    0.43
    oise
    0.43
    jsxFileName
    0.43
    extrait
    0.43
    fgets
    0.43
    Activations Density 0.001%

    No Known Activations