© 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. 5529
    Prev
    Next
    INDEX
    Explanations

    Sign ups

    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
     Вікі
    -0.56
    jkl
    -0.53
    Bibliograf
    -0.53
    weile
    -0.52
     Италијани
    -0.51
     CommonModule
    -0.51
     hers
    -0.51
    ModelAdmin
    -0.50
    INESS
    -0.50
    లాలు
    -0.50
    POSITIVE LOGITS
    出版年
    0.59
     if
    0.58
     to
    0.55
    <bos>
    0.53
    dentes
    0.50
    XPATH
    0.48
     while
    0.47
    findpost
    0.47
    érard
    0.45
    kheim
    0.45
    Activations Density 0.006%

    No Known Activations