© 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. 1-CLT-HP
    7. 12151
    Prev
    Next
    INDEX
    Explanations

    import

    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
    setDo
    -0.57
    ==",
    -0.56
     fédé
    -0.54
     FLAT
    -0.53
    IsUnicode
    -0.52
     MANAGER
    -0.52
    dify
    -0.52
    riwal
    -0.51
     }^{(
    -0.51
    يميديا
    -0.50
    POSITIVE LOGITS
    UnusedPrivate
    0.60
     segn
    0.57
    ADVERTISEMENT
    0.57
    ...');
    0.56
    KEYCODE
    0.55
     endforeach
    0.54
    دانشنامهٔ
    0.54
    ?>
    0.51
    BeginContext
    0.49
     elettrico
    0.49
    Activations Density 0.660%

    No Known Activations