© 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. 71626
    Prev
    Next
    INDEX
    Explanations

    side

    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
    In
    -0.18
    $
    -0.17
    It
    -0.17
    2
    -0.16
    The
    -0.16
    if
    -0.15
    I
    -0.15
    1
    -0.14
    3
    -0.14
    a
    -0.14
    POSITIVE LOGITS
     الرياضيه
    1.04
    AndEndTag
    1.02
    ^(@)
    1.02
     hâte
    0.93
     Мексичка
    0.88
    findpost
    0.85
     виправивши
    0.85
     peindre
    0.85
    ikusbot
    0.85
     $_"
    0.84
    Activations Density 0.006%

    No Known Activations