© 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. 0-RES-MATRYOSHKA-DC
    7. 11515
    Prev
    Next
    INDEX
    Explanations

    references to a specific document or section, such as citations or brackets

    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
     defaultstate
    -0.72
    LookAnd
    -0.71
    ]")]
    -0.64
    Whilst
    -0.63
    AsUp
    -0.57
     Whilst
    -0.51
    .*")]
    -0.48
     amongst
    -0.47
    aterdag
    -0.46
     فريبيس
    -0.46
    POSITIVE LOGITS
    webgl
    0.72
    WriteLiteral
    0.71
    jstor
    0.70
     ―――――
    0.68
    goku
    0.66
     ſch
    0.63
    THISDAY
    0.63
    المكان
    0.62
    PINES
    0.62
    ಿಸ
    0.61
    Activations Density 0.083%

    No Known Activations