© 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. 3386
    Prev
    Next
    INDEX
    Explanations

    a

    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
     betweenstory
    -0.55
     ethically
    -0.54
     prochaines
    -0.51
     محفوظة
    -0.49
    expandindo
    -0.48
    poptotic
    -0.48
    Fazit
    -0.48
     générations
    -0.47
    timate
    -0.47
     GeoNames
    -0.47
    POSITIVE LOGITS
    SBATCH
    0.62
    elemField
    0.58
    IsContent
    0.57
    期刊论文
    0.56
    帖最后由
    0.56
    HtmlAttribute
    0.55
    esModule
    0.54
    UNUSED
    0.54
    <bos>
    0.54
    شهاد
    0.52
    Activations Density 0.012%

    No Known Activations