© 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. 5-CLT-HP
    7. 94467
    Prev
    Next
    INDEX
    Explanations

    commas

    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
     surla
    -0.67
    原始内容存档于
    -0.57
    Designing
    -0.55
    <bos>
    -0.55
    Forrás
    -0.54
     בעל
    -0.54
     Савезне
    -0.54
    foglal
    -0.53
    "?>
    -0.52
    tvguidetime
    -0.52
    POSITIVE LOGITS
     CreateTagHelper
    0.60
    cshtml
    0.57
    utenant
    0.54
    цездатний
    0.53
    shafen
    0.52
    RotationOrder
    0.51
    atars
    0.50
    lankton
    0.50
    atella
    0.49
     cr
    0.48
    Activations Density 0.004%

    No Known Activations