© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41323
    Prev
    Next
    INDEX
    Explanations

    abbreviations

    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
     myſelf
    -2.28
     Efq
    -2.19
     itſelf
    -2.19
     Monfieur
    -2.14
    ſelf
    -2.03
     Jefus
    -2.03
     raiſ
    -1.96
     pleaſure
    -1.96
     ſche
    -1.95
     ſind
    -1.95
    POSITIVE LOGITS
     
    1.36
    ↵↵
    1.13
     (
    1.10
     The
    1.03
    .
    1.02
    /
    1.02
    i
    1.00
    ’
    1.00
    <eos>
    0.99
    '
    0.99
    Activations Density 0.058%

    No Known Activations