© 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. 5714
    Prev
    Next
    INDEX
    Explanations

    references to statistical model selection criteria and related scoring metrics

    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
     linkovi
    -0.56
    乓
    -0.52
    فیلم
    -0.50
    abaret
    -0.50
    THINGS
    -0.49
    σθαι
    -0.47
     GeoNames
    -0.47
    ltä
    -0.47
    newtheorem
    -0.46
    iverr
    -0.46
    POSITIVE LOGITS
    so
    1.15
    ser
    1.13
    sy
    1.12
    sw
    1.05
    sa
    1.02
    ses
    0.99
    sen
    0.99
    sob
    0.97
    son
    0.97
    su
    0.97
    Activations Density 0.275%

    No Known Activations