© 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. 4-CLT-HP
    7. 4314
    Prev
    Next
    INDEX
    Explanations

    Symbols and citations

    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
    <bos>
    -1.07
     kasarigan
    -0.52
     GNA
    -0.51
     executors
    -0.49
    تقاوى
    -0.49
     Bact
    -0.49
     Kyrgyzstan
    -0.47
    География
    -0.47
     reap
    -0.47
     Moors
    -0.47
    POSITIVE LOGITS
     négociations
    0.63
     enfans
    0.61
    Publié
    0.61
     modalités
    0.60
     fémin
    0.60
    vorschaubild
    0.59
    WriteLiteral
    0.59
     comportements
    0.58
     feroit
    0.58
     avoient
    0.58
    Activations Density 0.111%

    No Known Activations