© 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. 5-CLT-HP
    7. 4309
    Prev
    Next
    INDEX
    Explanations

    one

    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
     ModelExpression
    -0.62
    MigrationBuilder
    -0.61
     escar
    -0.47
    iterran
    -0.47
    arResult
    -0.46
     Interv
    -0.45
    LabelTagHelper
    -0.44
    СЯ
    -0.42
    Interv
    -0.42
    StoryboardSegue
    -0.41
    POSITIVE LOGITS
     of
    1.16
     leçons
    0.68
     prêtres
    0.68
     vérit
    0.67
     among
    0.67
     thing
    0.67
     satunya
    0.67
     vectorielle
    0.65
     voordeel
    0.62
     lecteurs
    0.61
    Activations Density 0.046%

    No Known Activations