© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13700
    Prev
    Next
    INDEX
    Explanations

    death

    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
     ModelExpression
    -0.82
    ValueStyle
    -0.76
     disambiguazione
    -0.73
    kloped
    -0.71
    **/
    -0.64
    Xna
    -0.61
    abestanden
    -0.60
     Spraw
    -0.60
     BoxDecoration
    -0.60
    autoconfigure
    -0.59
    POSITIVE LOGITS
     Rigidbody
    0.46
    ː
    0.46
     betweenstory
    0.43
     Clic
    0.41
    eslint
    0.41
     Carriers
    0.40
     Mehta
    0.40
    >{@
    0.40
     Lobby
    0.39
     referenties
    0.39
    Activations Density 0.034%

    No Known Activations