© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4943
    Prev
    Next
    INDEX
    Explanations

    measures related to signal or noise strength

    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
     strongly
    -0.74
    SuppressMessage
    -0.66
    strongly
    -0.66
    Strongly
    -0.57
    новниш
    -0.57
    HasForeignKey
    -0.56
    يكب
    -0.54
     prazo
    -0.54
     assolu
    -0.53
     kiin
    -0.53
    POSITIVE LOGITS
     strength
    3.00
     Strength
    2.84
    strength
    2.75
    Strength
    2.63
     STRENGTH
    2.50
     strengths
    2.27
    STRENGTH
    2.13
     Strengths
    1.98
     streng
    1.70
    Strengths
    1.63
    Activations Density 0.019%

    No Known Activations