© 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. 96440
    Prev
    Next
    INDEX
    Explanations

    bound

    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
    #
    -0.52
    GeneratedMessage
    -0.51
    rotnie
    -0.49
    eber
    -0.44
     Allí
    -0.44
    ราะ
    -0.43
    됨
    -0.43
    ][-
    -0.42
    ]--;
    -0.42
     Audiodateien
    -0.41
    POSITIVE LOGITS
     piedi
    0.70
     ModelExpression
    0.66
     Reader
    0.66
     Look
    0.65
     enfans
    0.65
    ValueStyle
    0.65
     Study
    0.64
     vicenda
    0.62
     Album
    0.62
     fourrure
    0.62
    Activations Density 0.009%

    No Known Activations