© 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. 5-CLT-HP
    7. 91123
    Prev
    Next
    INDEX
    Explanations

    revealing of information

    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
    UnusedPrivate
    -0.71
    Datuak
    -0.52
    saraba
    -0.52
    LookAnd
    -0.52
    CloseOperation
    -0.50
    netbeans
    -0.47
    ArrowToggle
    -0.47
    MERCIAL
    -0.45
    opes
    -0.45
    onte
    -0.45
    POSITIVE LOGITS
    Vorlage
    0.57
     afresh
    0.57
     WebDriverWait
    0.57
    iprot
    0.54
     in
    0.54
     darin
    0.53
    InSection
    0.53
     oprot
    0.52
    ,‎
    0.52
     Vikipedi
    0.52
    Activations Density 0.001%

    No Known Activations