© 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. 96085
    Prev
    Next
    INDEX
    Explanations

    volume

    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
     كومونز
    -0.63
     médicaux
    -0.55
     angelegt
    -0.54
    AnchorStyles
    -0.53
    REASON
    -0.50
     répon
    -0.47
     récon
    -0.46
     realistas
    -0.46
    Carcinogenicity
    -0.46
     énergé
    -0.46
    POSITIVE LOGITS
     jScrollPane
    0.65
     flow
    0.63
    Хьажоргаш
    0.61
    Flow
    0.55
    flow
    0.54
    adpleegd
    0.53
    reactivex
    0.52
    awtextra
    0.52
    rxjs
    0.52
    Serde
    0.52
    Activations Density 0.003%

    No Known Activations