© 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. 14695
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    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
     betweenstory
    -0.68
    στημα
    -0.55
    */),
    -0.50
    >>;
    -0.50
    caire
    -0.50
     Autorizaciones
    -0.50
     padi
    -0.49
     indisponible
    -0.49
     NDEBUG
    -0.48
     sender
    -0.48
    POSITIVE LOGITS
     EconPapers
    0.70
    UnsafeEnabled
    0.60
    Datuak
    0.60
     يتيمه
    0.58
    ArgsConstructor
    0.57
    bootstrapcdn
    0.52
     ostavi
    0.51
     worst
    0.48
    Portail
    0.48
    Tazama
    0.48
    Activations Density 0.007%

    No Known Activations