© 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. 6147
    Prev
    Next
    INDEX
    Explanations

    references to specific classes and categories of scientific and technical standards, conditions, or protocols

    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
    II
    -0.74
     II
    -0.63
     III
    -0.49
    غراف
    -0.47
    Il
    -0.47
     isKindOfClass
    -0.46
    tvguidetime
    -0.45
    nonatomic
    -0.44
    devamını
    -0.44
    MethodManager
    -0.43
    POSITIVE LOGITS
     виправивши
    0.76
    RTGC
    0.74
     дописавши
    0.71
    adpleegd
    0.68
     Савезне
    0.66
     biologique
    0.65
     automatiques
    0.65
     {}));
    0.64
    ksikon
    0.63
     باخ
    0.63
    Activations Density 0.210%

    No Known Activations