© 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. 3-RES-MATRYOSHKA-DC
    7. 165
    Prev
    Next
    INDEX
    Explanations

    code comments indicating the end of sections

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Krä
    -0.77
    aronder
    -0.71
     CURIAM
    -0.69
    üyada
    -0.68
    tvguidetime
    -0.66
    Rüyada
    -0.64
     INTERESAR
    -0.64
    UserScript
    -0.64
    afari
    -0.63
    Revenir
    -0.63
    POSITIVE LOGITS
     end
    2.86
     End
    2.72
     END
    2.55
    End
    2.52
     ends
    2.42
     Ends
    2.25
     ending
    2.09
    end
    2.06
     ended
    2.06
    END
    2.05
    Activations Density 1.744%

    No Known Activations