© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1825
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    0
    -0.90
    9
    -0.76
    6
    -0.70
    5
    -0.69
    8
    -0.68
    2
    -0.67
    1
    -0.65
    7
    -0.64
    3
    -0.63
    4
    -0.58
    POSITIVE LOGITS
    rungsseite
    0.93
    parsedMessage
    0.87
    mybatisplus
    0.85
     NSCoder
    0.85
    rrggbb
    0.83
    Билгалдахарш
    0.82
    ChildScrollView
    0.81
    VersionUID
    0.81
    ">—
    0.77
    MigrationBuilder
    0.73
    Activations Density 0.010%

    No Known Activations