© 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. 0-CLT-HP
    7. 42567
    Prev
    Next
    INDEX
    Explanations

    el di

    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
    URLException
    -0.82
     itſelf
    -0.80
     myſelf
    -0.79
     unſ
    -0.78
     himſelf
    -0.75
     houſe
    -0.75
    IsMutable
    -0.75
     للمعارف
    -0.74
     ſhall
    -0.73
     themſelves
    -0.72
    POSITIVE LOGITS
    hand
    0.47
    K
    0.42
    pace
    0.41
     grande
    0.41
    iker
    0.41
    one
    0.41
     K
    0.41
    grande
    0.40
    ever
    0.40
    C
    0.39
    Activations Density 0.078%

    No Known Activations