© 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. 1-CLT-HP
    7. 12345
    Prev
    Next
    INDEX
    Explanations

    remain

    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
     resourceCulture
    -0.69
    UnsafeEnabled
    -0.66
    SequentialGroup
    -0.60
    toHaveBeenCalled
    -0.57
    RuleContext
    -0.55
    scalatest
    -0.53
    iego
    -0.53
     book
    -0.53
    typeorm
    -0.52
     TestBed
    -0.51
    POSITIVE LOGITS
    .*")]
    0.60
     Himo
    0.50
     Kine
    0.47
    mbic
    0.47
     referenties
    0.47
    Integrated
    0.46
     Xperia
    0.46
     سكانية
    0.46
    uncios
    0.44
     atve
    0.44
    Activations Density 0.023%

    No Known Activations