© 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. 1-CLT-HP
    7. 665
    Prev
    Next
    INDEX
    Explanations

    Esq

    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
    Personendaten
    -0.80
     Khor
    -0.72
     Scy
    -0.66
    writeFieldEnd
    -0.66
    +#+#
    -0.60
     muualla
    -0.59
    évaluateur
    -0.59
    parsedMessage
    -0.59
     wireType
    -0.57
    CGPoint
    -0.57
    POSITIVE LOGITS
     InputDecoration
    0.56
    ウォ
    0.48
    Comté
    0.47
    клопе
    0.47
    verständ
    0.46
    az
    0.46
     tár
    0.45
    rshire
    0.45
     thuis
    0.44
    namb
    0.44
    Activations Density 0.018%

    No Known Activations