© 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. 14920
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
     resourceCulture
    -0.68
    UnusedPrivate
    -0.62
    };*/
    -0.62
     sonno
    -0.62
    trzyma
    -0.59
     hâte
    -0.58
    nestjs
    -0.57
     ſever
    -0.56
     ſein
    -0.55
    argout
    -0.55
    POSITIVE LOGITS
    WindowEvent
    0.56
     Kell
    0.52
     y
    0.51
    matchCondition
    0.50
     "..\..\..\
    0.49
     Y
    0.48
     Globo
    0.47
    vall
    0.47
    kampf
    0.46
    galus
    0.45
    Activations Density 0.018%

    No Known Activations