© 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. 94467
    Prev
    Next
    INDEX
    Explanations

    urgency or origin

    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
    derived
    -0.67
    marle
    -0.60
    Derived
    -0.57
     scrambled
    -0.56
     समीक्षाओं
    -0.56
     scramble
    -0.56
    UserScript
    -0.56
     propOrder
    -0.56
     scrambling
    -0.54
    minded
    -0.53
    POSITIVE LOGITS
    e
    0.53
    __((
    0.51
    føring
    0.51
    phate
    0.50
    ämän
    0.48
    irsi
    0.47
    esModule
    0.46
    angerie
    0.46
    AnchorTagHelper
    0.45
    GEBURTS
    0.45
    Activations Density 0.109%

    No Known Activations