© 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. 5895
    Prev
    Next
    INDEX
    Explanations

    descriptions of regression line slopes in figures

    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
     >=",
    -0.75
    Према
    -0.72
    Caj
    -0.71
     stack
    -0.69
    Tril
    -0.67
    huber
    -0.66
     تضيفلها
    -0.64
     Purification
    -0.64
     SwitchCompat
    -0.63
    ougou
    -0.62
    POSITIVE LOGITS
     slope
    3.19
     Slope
    2.88
    slope
    2.80
     slopes
    2.64
    Slope
    2.61
     sloping
    1.62
    slo
    1.51
    Slo
    1.48
     Slo
    1.47
     SLO
    1.34
    Activations Density 0.006%

    No Known Activations