© 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. 20-CLT-HP
    7. 76428
    Prev
    Next
    INDEX
    Explanations

    az

    np_max-act-logits · 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
     real
    -0.55
    zam
    -0.54
    zb
    -0.48
    z
    -0.48
     agent
    -0.47
    izr
    -0.46
     res
    -0.46
    zard
    -0.45
     agents
    -0.45
    zak
    -0.45
    POSITIVE LOGITS
     makeStyles
    0.70
    oles
    0.59
    StoreMessageInfo
    0.59
    migrationBuilder
    0.59
     متعلقه
    0.57
     насељу
    0.57
    InitVars
    0.57
    olen
    0.56
     Wikispecies
    0.56
    awtextra
    0.56
    Activations Density 0.017%

    No Known Activations