© 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. 1-CLT-HP
    7. 15903
    Prev
    Next
    INDEX
    Explanations

    stru

    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
     punches
    -0.96
     punch
    -0.87
    punch
    -0.77
     punching
    -0.67
     PUNCH
    -0.63
    rosine
    -0.60
     deposit
    -0.59
     Deposit
    -0.59
     Punch
    -0.59
     punched
    -0.58
    POSITIVE LOGITS
     Réponses
    0.59
     فريبيس
    0.54
    енча
    0.53
     CommonModule
    0.52
    StructEnd
    0.52
    AndEndTag
    0.50
    aarrggbb
    0.48
    __((
    0.48
     TestBed
    0.47
     BrowserModule
    0.47
    Activations Density 0.024%

    No Known Activations