© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92051
    Prev
    Next
    INDEX
    Explanations

    unstructured text

    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
    Portail
    -0.53
    GraphicsUnit
    -0.47
    consulté
    -0.46
     cu
    -0.46
     Fond
    -0.45
    WebServlet
    -0.44
     prote
    -0.43
    });*/
    -0.42
     Мексичка
    -0.42
    WireFormatLite
    -0.42
    POSITIVE LOGITS
     africains
    0.73
     auroit
    0.68
     للاسماء
    0.66
     démocr
    0.64
    Newswire
    0.64
    basicConfig
    0.64
     privées
    0.63
     sauvages
    0.63
     médicaux
    0.62
     pouvoit
    0.61
    Activations Density 0.279%

    No Known Activations