© 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. 94614
    Prev
    Next
    INDEX
    Explanations

    comparisons

    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
     valid
    -0.77
    valid
    -0.70
     GenerationType
    -0.67
     legitimate
    -0.65
    thinkable
    -0.65
    InSection
    -0.61
     authentic
    -0.60
    authentic
    -0.60
     inferior
    -0.59
    ROIT
    -0.59
    POSITIVE LOGITS
    ly
    0.94
    LY
    0.58
    ening
    0.50
    )$/,
    0.49
     prenn
    0.47
    )){
    0.45
     autorytatywna
    0.44
     esternos
    0.43
     مشين
    0.42
    ine
    0.42
    Activations Density 0.037%

    No Known Activations