© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11860
    Prev
    Next
    INDEX
    Explanations

    every

    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
    ↵
    -0.59
     dipakai
    -0.57
     renseignements
    -0.57
     pouvoirs
    -0.56
     Though
    -0.54
     pertes
    -0.52
     enfans
    -0.52
     químicas
    -0.51
     huiles
    -0.51
     découvertes
    -0.50
    POSITIVE LOGITS
     XNUMX
    0.95
    NUMX
    0.74
     Paglinawan
    0.69
     **/
    
    0.67
    $​
    0.66
    !';
    0.64
     myſelf
    0.63
    ')}}
    0.62
    '],
    
    0.60
    '])->
    0.60
    Activations Density 0.034%

    No Known Activations