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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 773
    Prev
    Next
    INDEX
    Explanations

    code

    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
    änomen
    -0.56
     planting
    -0.53
    émission
    -0.52
    ابس
    -0.50
    row
    -0.48
    yw
    -0.47
    Touches
    -0.47
     chain
    -0.47
     row
    -0.47
    leting
    -0.47
    POSITIVE LOGITS
    ValueStyle
    0.86
     CreateTagHelper
    0.68
    LookAnd
    0.60
    ("}\
    0.60
    >{@
    0.60
     surla
    0.59
    StoryboardSegue
    0.59
    contentLoaded
    0.57
    MigrationBuilder
    0.56
    ьаж
    0.55
    Activations Density 0.001%

    No Known Activations