© 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. 795
    Prev
    Next
    INDEX
    Explanations

    references to prior knowledge or previously mentioned information

    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
     كومونز
    -0.72
    fois
    -0.69
    Einzelnachweise
    -0.68
    Occasionally
    -0.65
     ehemaligen
    -0.65
     früheren
    -0.63
    chtest
    -0.63
     싶
    -0.61
    erunner
    -0.60
    <()>
    -0.59
    POSITIVE LOGITS
     already
    4.44
    already
    4.13
     Already
    4.06
    Already
    3.92
     ALREADY
    3.59
    ALREADY
    2.92
     allerede
    2.77
     déjà
    2.69
     redan
    2.69
     già
    2.53
    Activations Density 0.029%

    No Known Activations