© 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. 4-CLT-HP
    7. 772
    Prev
    Next
    INDEX
    Explanations

    to

    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
    uesia
    -0.84
    Tembelea
    -0.82
    
    -0.78
    thâu
    -0.77
     AspNetCore
    -0.76
    Notae
    -0.75
    jooq
    -0.72
    uxxxx
    -0.70
     Meksiku
    -0.70
    FieldBuilder
    -0.69
    POSITIVE LOGITS
     her
    0.49
     season
    0.44
     night
    0.44
     she
    0.44
     segn
    0.43
     two
    0.42
    她
    0.42
    yne
    0.41
    ughter
    0.40
     She
    0.40
    Activations Density 0.019%

    No Known Activations