© 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. 43237
    Prev
    Next
    INDEX
    Explanations

    arguments and statements

    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
    ագրություններ
    -0.71
     början
    -0.68
     tillbaka
    -0.66
     financières
    -0.65
     laikā
    -0.61
     larmes
    -0.60
     rodea
    -0.60
     cherchés
    -0.58
     igång
    -0.58
     möjligt
    -0.57
    POSITIVE LOGITS
    ing
    1.21
    ſelf
    1.20
     the
    1.20
    ments
    1.17
     Efq
    1.16
     purpoſe
    1.15
     Diſ
    1.14
     houſe
    1.13
     Jefus
    1.13
    ingly
    1.12
    Activations Density 0.109%

    No Known Activations