© 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. 39815
    Prev
    Next
    INDEX
    Explanations

    article

    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
    TargetException
    -0.82
    verwijspagina
    -0.72
    曖昧さ回避
    -0.71
     defaultstate
    -0.63
    تقاوى
    -0.63
    Geplaatst
    -0.62
     Paglinawan
    -0.62
    исленность
    -0.58
    ContentAsync
    -0.57
     incomplète
    -0.55
    POSITIVE LOGITS
     Cæsar
    0.70
     Jefus
    0.69
     Shakspeare
    0.64
     Ordovician
    0.63
     Shaksp
    0.62
    getStatusCode
    0.60
     Chrift
    0.59
     Houſe
    0.57
     Theorie
    0.57
     Majefty
    0.56
    Activations Density 0.118%

    No Known Activations