© 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. 38378
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     שוליים
    -0.98
     **/
    -0.90
    verwijspagina
    -0.88
     مشين
    -0.84
    ^(@)
    -0.84
    principalTable
    -0.83
     disambiguazione
    -0.83
     ویکی‌پدی
    -0.81
     >=",
    -0.80
     snippetHide
    -0.79
    POSITIVE LOGITS
    <bos>
    0.59
    R
    0.43
     
    0.40
    B
    0.39
    ↵
    0.39
    1
    0.39
    H
    0.38
    G
    0.38
    A
    0.38
     lopp
    0.37
    Activations Density 0.025%

    No Known Activations