© 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. 42225
    Prev
    Next
    INDEX
    Explanations

    arter

    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
    setVerticalGroup
    -0.71
     getItemId
    -0.64
     FRUIT
    -0.56
    Архівовано
    -0.55
     resourceCulture
    -0.54
     Fruit
    -0.52
    蜒
    -0.52
    fruit
    -0.51
    Fruit
    -0.51
    onite
    -0.51
    POSITIVE LOGITS
    e
    0.65
     Nacionales
    0.59
    setImageBitmap
    0.57
    As
    0.56
     Tour
    0.54
    Tour
    0.53
    P
    0.53
    ian
    0.52
    And
    0.52
    ScopeManager
    0.52
    Activations Density 1.640%

    No Known Activations