© 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. 5-CLT-HP
    7. 96060
    Prev
    Next
    INDEX
    Explanations

    months

    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
    koń
    -0.49
    xffffffff
    -0.47
     Hodges
    -0.46
     Ica
    -0.45
    AYE
    -0.43
    oodoo
    -0.43
     spojen
    -0.43
    NELL
    -0.43
    érard
    -0.43
    LN
    -0.42
    POSITIVE LOGITS
     vPvB
    0.67
    unknownFields
    0.65
    addCriterion
    0.64
    wpi
    0.62
    TagMode
    0.61
    homonymie
    0.58
    кономі
    0.58
    adpleegd
    0.57
    CloseOperation
    0.56
    SourceChecksum
    0.55
    Activations Density 0.008%

    No Known Activations