© 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. 43258
    Prev
    Next
    INDEX
    Explanations

    systematic reviews and dates

    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
    DockStyle
    -0.75
    UserScript
    -0.73
    Datuak
    -0.71
    Ārējās
    -0.71
    principalColumn
    -0.69
     onAnimation
    -0.69
    migrationBuilder
    -0.68
    ItemBackground
    -0.68
     ainfi
    -0.68
     IndexError
    -0.67
    POSITIVE LOGITS
     other
    0.53
     tanke
    0.53
    eed
    0.52
    상
    0.49
    imal
    0.47
    ee
    0.47
    govina
    0.47
    epro
    0.46
     nature
    0.45
    eee
    0.44
    Activations Density 0.215%

    No Known Activations