© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 636
    Prev
    Next
    INDEX
    Explanations

    felonies

    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
     مرئيه
    -0.67
     useAppContext
    -0.57
     estekak
    -0.53
    DockStyle
    -0.50
    
    -0.49
    kuuta
    -0.47
    sizeCache
    -0.47
    Portail
    -0.47
    tagHelperRunner
    -0.47
    وره
    -0.47
    POSITIVE LOGITS
     myſelf
    0.63
     ASN
    0.56
     Misses
    0.55
     Somerville
    0.54
     Defendants
    0.53
    følgelig
    0.53
     itſelf
    0.52
     Affiliations
    0.52
     officiels
    0.52
     euer
    0.52
    Activations Density 0.005%

    No Known Activations