© 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. 5-CLT-HP
    7. 92508
    Prev
    Next
    INDEX
    Explanations

    study

    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
     Normdatei
    -0.65
    বহ
    -0.57
    RectangleBorder
    -0.57
    ագրություններ
    -0.55
     flesta
    -0.52
     MaterialApp
    -0.51
     joindre
    -0.50
     pymongo
    -0.49
    migrationBuilder
    -0.49
     meeste
    -0.49
    POSITIVE LOGITS
    expandindo
    0.67
     betweenstory
    0.61
    tième
    0.59
     of
    0.58
    曖昧さ回避
    0.55
    AndEndTag
    0.51
    JsonInclude
    0.50
    ierenden
    0.49
    thenia
    0.48
     Concerned
    0.48
    Activations Density 0.004%

    No Known Activations