© 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. 5-CLT-HP
    7. 95020
    Prev
    Next
    INDEX
    Explanations

    permission, capability

    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
    تقاوى
    -1.08
    OGND
    -0.98
    脚注の使い方
    -0.98
    ագրություններ
    -0.96
    featureID
    -0.96
     disambiguazione
    -0.95
     مشين
    -0.94
    ScopeManager
    -0.93
    PerformLayout
    -0.91
    GenerationType
    -0.91
    POSITIVE LOGITS
    getWindow
    0.32
     as
    0.30
     както
    0.30
     az
    0.30
    richtet
    0.29
    asje
    0.29
    zewod
    0.28
     zda
    0.28
     dej
    0.28
     objectForKey
    0.27
    Activations Density 0.002%

    No Known Activations