© 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. 96567
    Prev
    Next
    INDEX
    Explanations

    code/configuration files

    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
     незавершена
    -0.75
     дописавши
    -0.71
    ніципалі
    -0.67
    Geplaatst
    -0.65
     utafitiHapana
    -0.62
     صوتيه
    -0.62
    mybatisplus
    -0.60
    PreferredItem
    -0.58
    脚注の使い方
    -0.58
     समीक्षाओं
    -0.57
    POSITIVE LOGITS
    <eos>
    0.64
    :
    0.59
     (
    0.58
    c
    0.55
     or
    0.55
     code
    0.52
    d
    0.52
    RDONLY
    0.49
    r
    0.49
    n
    0.48
    Activations Density 0.007%

    No Known Activations