© 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. 1-CLT-HP
    7. 9079
    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
    脚注の使い方
    -0.77
    Portail
    -0.76
    انيف
    -0.73
     CreateTagHelper
    -0.70
    principalColumn
    -0.63
     față
    -0.62
     Occidental
    -0.61
     дописавши
    -0.61
     Lijst
    -0.60
     itſelf
    -0.60
    POSITIVE LOGITS
     man
    0.53
     who
    0.49
    #+#
    0.46
     deliver
    0.46
    \|^{
    0.45
     une
    0.45
    sidemargin
    0.45
     trial
    0.44
    kolen
    0.44
    volved
    0.44
    Activations Density 0.108%

    No Known Activations