© 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. 20-CLT-HP
    7. 74622
    Prev
    Next
    INDEX
    Explanations

    programming code/documentation

    np_max-act-logits · 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
    })));
    -0.55
    ))));
    -0.52
    parseFrom
    -0.49
    tanleria
    -0.48
     ujednoznacz
    -0.47
    wikidata
    -0.47
     CanadaChoose
    -0.46
     Xa
    -0.46
     SAB
    -0.45
    ()")
    -0.45
    POSITIVE LOGITS
    出版年
    0.63
     strijd
    0.56
     Accesat
    0.55
     AppColors
    0.55
     Methuen
    0.54
    protoc
    0.54
    ModelBuilder
    0.52
     gynhyrchwyd
    0.52
     '\\;'
    0.51
    Depth
    0.51
    Activations Density 0.001%

    No Known Activations