© 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. 98199
    Prev
    Next
    INDEX
    Explanations

    in

    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
    MigrationBuilder
    -0.68
    ,:),
    -0.61
    unnitel
    -0.60
    BagLayout
    -0.57
    endfor
    -0.56
    setVerticalGroup
    -0.55
    حياته
    -0.55
    holtz
    -0.55
    viously
    -0.54
    agai
    -0.54
    POSITIVE LOGITS
     from
    0.82
    homonymie
    0.54
     từ
    0.46
     off
    0.45
     dari
    0.45
    mixture
    0.43
    iprot
    0.41
     Domes
    0.41
    จาก
    0.40
    Referanser
    0.39
    Activations Density 0.000%

    No Known Activations