© 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. 20-CLT-HP
    7. 75012
    Prev
    Next
    INDEX
    Explanations

    Mixed and varied text

    np_max-act-logits · 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
    RuleContext
    -0.58
     '\\;'
    -0.58
    lias
    -0.57
    Datuak
    -0.54
    rosh
    -0.54
     '.';
    -0.54
     '/';
    -0.53
    ]")]
    -0.53
    ########.
    -0.52
    บล
    -0.52
    POSITIVE LOGITS
     nonUne
    0.63
    SourceChecksum
    0.59
    mybatisplus
    0.58
    曖昧さ回避
    0.57
    πάρχ
    0.56
    available
    0.52
     disponibilité
    0.50
    mucha
    0.49
    sizeCache
    0.48
    addCriterion
    0.48
    Activations Density 0.002%

    No Known Activations