© 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. 1-CLT-HP
    7. 45737
    Prev
    Next
    INDEX
    Explanations

    transitional adverbs

    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
     noDo
    -0.47
    Inet
    -0.45
    umque
    -0.45
    vician
    -0.44
     computational
    -0.43
     Advis
    -0.42
     нами
    -0.42
     Computing
    -0.41
    ''');
    -0.41
    ]=="
    -0.41
    POSITIVE LOGITS
    <bos>
    0.75
    MigrationBuilder
    0.73
     defaultstate
    0.70
    DockStyle
    0.66
     الرياضيه
    0.65
    onViewCreated
    0.65
    RetentionPolicy
    0.64
    esModule
    0.61
    #
    0.56
    modelBuilder
    0.56
    Activations Density 0.244%

    No Known Activations