© 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. 4-CLT-HP
    7. 13
    Prev
    Next
    INDEX
    Explanations

    cokinetic

    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
    cokinetic
    -1.01
    cokinetics
    -1.00
     للاسماء
    -0.55
    ThroughAttribute
    -0.52
    adpleegd
    -0.51
     geográfica
    -0.50
     TextAlign
    -0.50
    Ссылки
    -0.48
    geqslant
    -0.48
    googleapis
    -0.47
    POSITIVE LOGITS
    MessageTagHelper
    0.66
     متعلقه
    0.64
     BoxFit
    0.63
    principalTable
    0.58
    AndEndTag
    0.57
     Pardo
    0.56
    MigrationBuilder
    0.53
    RenderAtEndOf
    0.51
    '][]
    0.51
     adulte
    0.51
    Activations Density 0.010%

    No Known Activations