© 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. 4-CLT-HP
    7. 522
    Prev
    Next
    INDEX
    Explanations

    numbers 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
    Viited
    -0.57
     bár
    -0.54
     kiu
    -0.54
     jsPsych
    -0.54
     HasFactory
    -0.54
    YNC
    -0.51
     useCallback
    -0.50
    peicher
    -0.50
     associés
    -0.50
     Maher
    -0.50
    POSITIVE LOGITS
    OGND
    0.85
     nahilalakip
    0.65
    期刊论文
    0.63
    
    0.60
    ThroughAttribute
    0.60
    parsedMessage
    0.59
     beginnetje
    0.56
    cros
    0.56
    حياته
    0.54
    tagHelperRunner
    0.54
    Activations Density 0.000%

    No Known Activations