© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95736
    Prev
    Next
    INDEX
    Explanations

    blog posts and articles

    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
    Negative Logits
     imagine
    -0.67
     wouldn
    -0.57
     reading
    -0.49
    yty
    -0.48
    σσ
    -0.47
    iger
    -0.47
    igar
    -0.45
    typed
    -0.44
     cruz
    -0.44
    :✨
    -0.44
    POSITIVE LOGITS
    ſelves
    0.82
    ſelf
    0.79
     مرئيه
    0.74
     الحره
    0.71
     Roskov
    0.71
    SourceChecksum
    0.69
    цездатний
    0.65
     ExecuteAsync
    0.64
     صوتيه
    0.63
    >");
    0.61
    Activations Density 0.177%

    No Known Activations