© 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. 20-CLT-HP
    7. 77925
    Prev
    Next
    INDEX
    Explanations

    Code and computer snippets

    np_max-act-logits · 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
     itſelf
    -0.83
     ModelExpression
    -0.83
     purpoſe
    -0.81
     houſe
    -0.77
     يتيمه
    -0.73
     myſelf
    -0.72
     quæ
    -0.72
     himſelf
    -0.71
     ſtate
    -0.71
     Forumite
    -0.69
    POSITIVE LOGITS
    '
    0.62
     is
    0.57
     are
    0.57
    ’
    0.54
     can
    0.52
     Can
    0.51
    Can
    0.49
     CAN
    0.48
     Have
    0.45
     Are
    0.45
    Activations Density 0.017%

    No Known Activations