© 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. 3100
    Prev
    Next
    INDEX
    Explanations

    references to discussion or analysis of numerical results

    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
     conversation
    -1.11
     talking
    -0.98
     conversations
    -0.95
     talk
    -0.93
    conversation
    -0.88
    talk
    -0.87
    Talk
    -0.86
    talking
    -0.86
     dialogue
    -0.83
     Talking
    -0.80
    POSITIVE LOGITS
     discussed
    1.30
    discussed
    1.22
    cussed
    1.03
     discusses
    0.93
     للمعارف
    0.91
     discuss
    0.88
    colgroup
    0.79
     Discuss
    0.77
    principalColumn
    0.77
    最快更新
    0.76
    Activations Density 0.014%

    No Known Activations