© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1860
    Prev
    Next
    INDEX
    Explanations

    the

    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
     our
    -0.49
     ComVisible
    -0.49
     artikkelen
    -0.47
    뜻
    -0.46
    mybatisplus
    -0.46
    poken
    -0.45
     NSError
    -0.44
     BorderRadius
    -0.43
    stdc
    -0.41
    ounder
    -0.41
    POSITIVE LOGITS
     conversation
    0.69
     endwhile
    0.67
    conversation
    0.65
     miliardi
    0.60
    RenderAtEndOf
    0.59
    MigrationBuilder
    0.57
     {!
    0.57
     olvides
    0.56
    ırken
    0.56
    хьтан
    0.56
    Activations Density 0.004%

    No Known Activations