© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3510
    Prev
    Next
    INDEX
    Explanations

    why or reason

    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
     bevis
    -0.60
    >*/
    -0.54
     entanto
    -0.51
     preuves
    -0.50
    Therefore
    -0.49
     basée
    -0.49
    therefore
    -0.49
    herited
    -0.49
     חיצוניים
    -0.48
     *)__
    -0.48
    POSITIVE LOGITS
    ,
    0.95
     it
    0.77
     we
    0.65
    Бахар
    0.59
    новниш
    0.59
    webElementXpaths
    0.57
    ;
    0.57
     they
    0.56
     I
    0.56
    ftagPool
    0.55
    Activations Density 0.003%

    No Known Activations