© 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. 39909
    Prev
    Next
    INDEX
    Explanations

    relentless

    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
    bibinfo
    -0.64
    Autoritní
    -0.62
    BibitemShut
    -0.62
    bibfield
    -0.60
    principalColumn
    -0.60
    blauch
    -0.57
    ctu
    -0.57
    gjenge
    -0.56
    >\<^
    -0.55
    elfth
    -0.53
    POSITIVE LOGITS
    Geplaatst
    0.79
    kembang
    0.67
    expandindo
    0.65
     Roskov
    0.65
    ########.
    0.64
    ArrowToggle
    0.53
     tématu
    0.53
     Réponses
    0.52
    XmlAccessType
    0.50
    หวัด
    0.50
    Activations Density 1.453%

    No Known Activations