© 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. 6277
    Prev
    Next
    INDEX
    Explanations

    references to the amount of similarity or degree of comparison

    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
    IntoConstraints
    -0.56
    extAlignment
    -0.52
    +#+#
    -0.51
    ibatis
    -0.49
    حن
    -0.48
    //
    -0.46
     कथ
    -0.46
    arcoma
    -0.46
    штей
    -0.46
     Zahl
    -0.45
    POSITIVE LOGITS
    few
    0.72
     briefly
    0.71
     breve
    0.70
    ]]
    0.69
    ISupport
    0.68
    PerformLayout
    0.66
     sparingly
    0.65
     FEW
    0.65
     brevemente
    0.65
    abestanden
    0.63
    Activations Density 0.215%

    No Known Activations