© 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. 39989
    Prev
    Next
    INDEX
    Explanations

    file headers/metadata

    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
    })));
    -0.71
    elemField
    -0.66
    modelBuilder
    -0.59
    });*/
    -0.59
    avadoc
    -0.59
     محفوظة
    -0.58
    RUPT
    -0.55
    Vidite
    -0.55
    }*/
    -0.54
     AssemblyTitle
    -0.54
    POSITIVE LOGITS
    ագրություններ
    0.63
    kháu
    0.56
     NSCoder
    0.54
     çıkan
    0.51
    unref
    0.51
    Décès
    0.50
     romanos
    0.50
    (/^
    0.49
    Tembelea
    0.49
    יקר
    0.48
    Activations Density 0.068%

    No Known Activations