© 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. 94064
    Prev
    Next
    INDEX
    Explanations

    processes/procedures

    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
     mixing
    -0.69
     autorytatywna
    -0.69
     للاسماء
    -0.69
     Mixing
    -0.67
    Immediately
    -0.65
    rawDesc
    -0.65
    Mixing
    -0.63
    BeforeEach
    -0.62
     meet
    -0.60
    UnusedPrivate
    -0.60
    POSITIVE LOGITS
    ="#"><
    0.57
    osovo
    0.53
     sor
    0.53
    anskje
    0.53
    äki
    0.50
     drop
    0.48
    },[
    0.48
    ResponseWriter
    0.47
    icana
    0.47
     −
    0.47
    Activations Density 0.054%

    No Known Activations