© 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. 13109
    Prev
    Next
    INDEX
    Explanations

    Question words

    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
    contentLoaded
    -0.61
    principalColumn
    -0.58
     fermés
    -0.57
    oa̍t
    -0.57
    RenderAtEndOf
    -0.55
     mukana
    -0.53
    ">//
    -0.53
    WriteTagHelper
    -0.52
     masina
    -0.52
     leçons
    -0.52
    POSITIVE LOGITS
     instead
    0.57
    ỡng
    0.55
     actually
    0.54
     OFDb
    0.53
     according
    0.53
     muualla
    0.52
     समीक्षक
    0.50
    стота
    0.50
     generally
    0.50
     Raj
    0.49
    Activations Density 0.043%

    No Known Activations