© 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. 607
    Prev
    Next
    INDEX
    Explanations

    reasons explaining the primary cause or justification for a statement or decision

    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
    source
    -0.95
    Source
    -0.90
     source
    -0.90
     Source
    -0.83
    sources
    -0.81
     fonte
    -0.79
    源
    -0.78
     sources
    -0.78
    src
    -0.76
     src
    -0.76
    POSITIVE LOGITS
     reason
    4.22
    reason
    3.61
     reasons
    3.56
     Reason
    3.50
    Reason
    3.41
     Reasons
    3.16
     REASON
    3.14
    reasons
    3.13
    Reasons
    2.95
    REASON
    2.73
    Activations Density 0.026%

    No Known Activations