© 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. 5-CLT-HP
    7. 92416
    Prev
    Next
    INDEX
    Explanations

    nobel

    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
     quæ
    -0.84
     <=",
    -0.81
    Patterns
    -0.75
    patterns
    -0.72
    ListItemIcon
    -0.71
     NDEBUG
    -0.69
    Gemeinden
    -0.69
    ArgsConstructor
    -0.68
    WillAppear
    -0.68
     stiefel
    -0.67
    POSITIVE LOGITS
     côtés
    0.43
     prochaines
    0.42
    ウマ
    0.42
     numerus
    0.39
     alongside
    0.38
     parler
    0.38
    abestanden
    0.37
    ,{\
    0.36
    هذه
    0.36
     مشين
    0.36
    Activations Density 0.001%

    No Known Activations