© 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. 402
    Prev
    Next
    INDEX
    Explanations

    historic

    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
    WriteBarrier
    -0.60
    fjspx
    -0.58
    +#+
    -0.55
    paravant
    -0.55
    PreferredItem
    -0.46
    ISPR
    -0.46
     Historical
    -0.45
    Historical
    -0.44
    #!/
    -0.44
     HISTORICAL
    -0.43
    POSITIVE LOGITS
    
    0.67
     BoxDecoration
    0.62
    Begriffsklä
    0.57
     Tapatalk
    0.55
    openapi
    0.51
    WindowConstants
    0.50
    moveToFirst
    0.50
    Visitation
    0.50
    coroutines
    0.49
    chend
    0.48
    Activations Density 0.002%

    No Known Activations