© 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. 1988
    Prev
    Next
    INDEX
    Explanations

    locations/places

    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
     Efq
    -1.84
     Monfieur
    -1.73
     myſelf
    -1.66
     itſelf
    -1.48
     Theſe
    -1.47
     Diſ
    -1.45
     Anſ
    -1.45
     doubtnut
    -1.45
     ―――――
    -1.44
     Majefty
    -1.43
    POSITIVE LOGITS
     
    0.68
     M
    0.68
     S
    0.65
     (
    0.63
     G
    0.63
     B
    0.62
    ↵
    0.61
     A
    0.59
    '
    0.59
     C
    0.58
    Activations Density 1.639%

    No Known Activations