© 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. 42517
    Prev
    Next
    INDEX
    Explanations

    October

    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
     October
    -1.50
     August
    -1.49
     July
    -1.45
     April
    -1.28
     Oct
    -1.24
     Aug
    -1.23
     June
    -1.17
    October
    -1.17
    July
    -1.16
     January
    -1.13
    POSITIVE LOGITS
     isoto
    0.74
     disparu
    0.71
     Originals
    0.70
     Swelling
    0.70
     Sleeve
    0.69
     Coefficients
    0.69
     Stimulation
    0.68
     Gypsum
    0.68
     Nominations
    0.68
     Sleeves
    0.68
    Activations Density 0.163%

    No Known Activations