© 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. 0-CLT-HP
    7. 38429
    Prev
    Next
    INDEX
    Explanations

    consecutive

    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
     decade
    -1.08
     inform
    -0.91
     consecutive
    -0.91
     Inform
    -0.91
     Decade
    -0.89
    Inform
    -0.86
    MigrationBuilder
    -0.82
     Normdatei
    -0.82
    OGND
    -0.79
    ImageContext
    -0.79
    POSITIVE LOGITS
    inare
    0.47
    ress
    0.44
     in
    0.43
    s
    0.43
    Reproduced
    0.42
    IGNS
    0.41
    an
    0.41
    ydable
    0.41
    getAdapter
    0.40
    <bos>
    0.40
    Activations Density 1.054%

    No Known Activations