© 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. 45247
    Prev
    Next
    INDEX
    Explanations

    exactly limited

    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
     nécessité
    -0.57
     uitzicht
    -0.56
     quæ
    -0.54
     nessuna
    -0.54
     mitään
    -0.53
    berdayakan
    -0.52
     كومونز
    -0.52
     nessun
    -0.51
     miatt
    -0.50
     gratuits
    -0.50
    POSITIVE LOGITS
    +#+#
    0.77
     initComponents
    0.62
     Semp
    0.61
     createSlice
    0.59
    таратура
    0.57
    Linq
    0.57
    invokeLater
    0.57
    })();
    0.56
     dụ
    0.53
    DataPropertyName
    0.53
    Activations Density 0.069%

    No Known Activations