© 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. 5-CLT-HP
    7. 4655
    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
    migrationBuilder
    -0.67
     Процитовано
    -0.65
     kaynağından
    -0.64
    Legături
    -0.60
    HasForeignKey
    -0.59
    CloseOperation
    -0.59
     Smarty
    -0.58
    참고
    -0.57
    contentLoaded
    -0.56
    Referencie
    -0.56
    POSITIVE LOGITS
    forChild
    0.52
    AttributeSet
    0.51
    
    0.50
    unshift
    0.49
    mtrl
    0.49
    neri
    0.47
    conom
    0.45
     sound
    0.45
    udd
    0.44
     ног
    0.44
    Activations Density 0.006%

    No Known Activations