© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73426
    Prev
    Next
    INDEX
    Explanations

    Social media

    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
     himſelf
    -0.63
     Arxivat
    -0.58
    +#+
    -0.56
     attendee
    -0.56
     vengan
    -0.55
    ARROLL
    -0.55
     fumar
    -0.55
     muſt
    -0.55
     ſhe
    -0.54
     poffible
    -0.54
    POSITIVE LOGITS
     end
    0.66
     StatefulWidget
    0.61
    end
    0.59
    ArgsConstructor
    0.58
    protoimpl
    0.56
     StatelessWidget
    0.54
     HasFactory
    0.53
     End
    0.53
     Nutz
    0.52
    CppMethod
    0.52
    Activations Density 0.001%

    No Known Activations