© 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. 94710
    Prev
    Next
    INDEX
    Explanations

    Bryce

    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
    -1.20
     autorytatywna
    -1.11
    NUMX
    -1.10
     ―――――
    -1.09
     myſelf
    -1.06
     ་་
    -1.04
    enumi
    -1.02
    Personensuche
    -1.02
    ſelves
    -1.00
     متعلقه
    -0.98
    POSITIVE LOGITS
     and
    0.73
    i
    0.72
    ,
    0.72
     (
    0.70
     
    0.70
    a
    0.68
    o
    0.68
     or
    0.66
    /
    0.65
    <eos>
    0.64
    Activations Density 0.653%

    No Known Activations