© 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. 20-CLT-HP
    7. 76610
    Prev
    Next
    INDEX
    Explanations

    Brands and programming errors

    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
     HasFactory
    -0.63
     يتيمه
    -0.63
    
    -0.61
    hyrchwyd
    -0.58
    GenerationType
    -0.58
    RTEX
    -0.58
    IntoConstraints
    -0.57
    δί
    -0.57
     autorytatywna
    -0.57
     intptr
    -0.56
    POSITIVE LOGITS
     Air
    0.69
    Air
    0.57
     air
    0.55
    getDoctrine
    0.53
    PointerException
    0.50
    air
    0.50
     AIR
    0.46
    AIR
    0.44
     alá
    0.43
     Dame
    0.43
    Activations Density 0.005%

    No Known Activations