© 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. 1-CLT-HP
    7. 10013
    Prev
    Next
    INDEX
    Explanations

    Although

    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
     ویکی‌پدیا
    -0.63
     resourceCulture
    -0.53
     AssemblyCulture
    -0.52
     propOrder
    -0.50
     Signalez
    -0.50
    tagext
    -0.49
    +#+#
    -0.46
    IsContent
    -0.46
     EoL
    -0.43
    ิลป
    -0.42
    POSITIVE LOGITS
     perjury
    0.64
     baptized
    0.59
     robbed
    0.58
     hacked
    0.58
    )_/¯
    0.57
     dragged
    0.57
     sentenced
    0.57
     dissatisfaction
    0.56
     humiliated
    0.56
     dissatisfied
    0.56
    Activations Density 0.008%

    No Known Activations