© 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. 1-CLT-HP
    7. 10273
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     itſelf
    -1.16
     myſelf
    -1.06
     Jefus
    -1.04
     himſelf
    -1.00
     Efq
    -0.99
     purpoſe
    -0.98
     themſelves
    -0.96
     ModelExpression
    -0.95
     poffe
    -0.95
     Monfieur
    -0.94
    POSITIVE LOGITS
     (
    0.67
     
    0.65
    (
    0.59
    has
    0.58
    long
    0.57
    to
    0.57
    net
    0.53
     m
    0.53
    not
    0.52
     ex
    0.52
    Activations Density 0.006%

    No Known Activations