© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5321
    Prev
    Next
    INDEX
    Explanations

    code and dates

    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
    or
    -0.45
    ar
    -0.42
    one
    -0.41
    á
    -0.40
    is
    -0.40
    p
    -0.40
    no
    -0.39
    io
    -0.39
    un
    -0.39
    v
    -0.38
    POSITIVE LOGITS
     ویکی‌پدی
    1.00
     betweenstory
    0.88
    <bos>
    0.87
    BeginContext
    0.86
    @[+][
    0.86
    ftagPool
    0.84
    دانشنامهٔ
    0.83
    '},
    0.83
    — 
    0.82
    awtextra
    0.80
    Activations Density 0.004%

    No Known Activations