© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38798
    Prev
    Next
    INDEX
    Explanations

    government/state news

    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
     neuve
    -0.57
    ibatis
    -0.54
     />);
    -0.54
     prêts
    -0.54
     />;
    -0.53
     šo
    -0.52
    })*/
    -0.51
    ništ
    -0.49
     fermés
    -0.49
     flecha
    -0.49
    POSITIVE LOGITS
     noDo
    0.68
    webElementXpaths
    0.66
     resourceCulture
    0.63
    mrow
    0.62
     ostavi
    0.61
     GenerationType
    0.60
    opsida
    0.59
    RectangleBorder
    0.58
     CURIAM
    0.57
    brook
    0.56
    Activations Density 0.046%

    No Known Activations