© 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. 3873
    Prev
    Next
    INDEX
    Explanations

    references to specific notable events or entities, often marked by uppercase words and numerical indicators

    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
    уда
    -0.61
    providedIn
    -0.60
    __':
    -0.56
     ๆ
    -0.55
    ='';
    -0.55
    brainly
    -0.55
     Sau
    -0.53
     unt
    -0.53
    ---|---|
    -0.52
    Amicalement
    -0.52
    POSITIVE LOGITS
    GEBURTSDATUM
    0.85
     anún
    0.82
     avoient
    0.79
     étoit
    0.75
     étoient
    0.74
     auroit
    0.74
     travailleurs
    0.74
     theologians
    0.73
     estadounid
    0.72
     Serbs
    0.72
    Activations Density 0.504%

    No Known Activations