© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 782
    Prev
    Next
    INDEX
    Explanations

    locations

    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
     Kaufmann
    -0.48
    ystic
    -0.48
    lijkheid
    -0.46
     $\
    -0.46
    endpush
    -0.44
     Fu
    -0.43
    fører
    -0.43
    金山
    -0.42
    ц
    -0.42
    POSITIVE LOGITS
    parsedMessage
    0.84
    IUrlHelper
    0.76
    UrlResolution
    0.72
     ſche
    0.71
    InjectAttribute
    0.71
    /*
    0.69
     itſelf
    0.67
     ―――――
    0.65
     raiſ
    0.65
    TagMode
    0.65
    Activations Density 0.036%

    No Known Activations