© 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. 2-RES-MATRYOSHKA-DC
    7. 3711
    Prev
    Next
    INDEX
    Explanations

    statements of contention or assertion

    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
    mappedBy
    -0.74
    libft
    -0.61
    })`
    -0.61
     Lek
    -0.57
    opsida
    -0.56
     Albright
    -0.55
     ‘
    -0.55
     Talk
    -0.55
    MatInputModule
    -0.54
    RenderAtEndOf
    -0.54
    POSITIVE LOGITS
     contend
    2.38
     contends
    2.14
     contended
    2.03
     contention
    1.95
     contending
    1.93
     contentions
    1.75
     Cont
    1.16
    conten
    1.14
     contender
    1.02
     contenders
    1.02
    Activations Density 0.009%

    No Known Activations