© 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. 92591
    Prev
    Next
    INDEX
    Explanations

    to

    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
     consultato
    -0.77
     CURIAM
    -0.69
    getOut
    -0.55
     cliquant
    -0.54
     Préférences
    -0.53
    adpleegd
    -0.52
    Posters
    -0.52
     InputDecoration
    -0.52
    Enllaces
    -0.52
    })();
    -0.52
    POSITIVE LOGITS
     незавершена
    0.59
     spend
    0.57
     express
    0.56
     lenker
    0.48
     learn
    0.48
    corrhi
    0.47
     explore
    0.47
     rethink
    0.47
    SharedDtor
    0.46
    PreferredItem
    0.46
    Activations Density 0.003%

    No Known Activations