© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3319
    Prev
    Next
    INDEX
    Explanations

    locations

    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
    FetchType
    -0.41
     Gar
    -0.35
     φ
    -0.32
     CYTHON
    -0.32
     sino
    -0.32
     pytest
    -0.30
    ib
    -0.29
    MENAFN
    -0.29
    gad
    -0.28
     brand
    -0.28
    POSITIVE LOGITS
    AccessorTable
    0.93
    ]-->
    0.84
    URLException
    0.80
     itſelf
    0.80
     @"/
    0.79
     himſelf
    0.78
    ItemBackground
    0.78
    PointerException
    0.77
     raiſ
    0.77
    Comté
    0.75
    Activations Density 0.000%

    No Known Activations