© 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. 1-RES-MATRYOSHKA-DC
    7. 359
    Prev
    Next
    INDEX
    Explanations

    descriptions of structural or qualitative modifications

    oai_token-act-pair · gpt-4.1-nano
    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
    RenderAtEndOf
    -0.71
    providedIn
    -0.71
    InputBorder
    -0.70
     AssemblyCulture
    -0.66
     nakalista
    -0.63
    Portale
    -0.62
    (||
    -0.62
     proprement
    -0.60
     reprodução
    -0.59
     שוליים
    -0.57
    POSITIVE LOGITS
     change
    3.94
     changes
    3.86
     Change
    3.59
     Changes
    3.56
    change
    3.48
    changes
    3.45
    Change
    3.44
    Changes
    3.31
     CHANGE
    3.31
     changed
    3.27
    Activations Density 1.342%

    No Known Activations