© 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. 3582
    Prev
    Next
    INDEX
    Explanations

    references to suggested hints or recommendations

    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
     contextLoads
    -0.80
    sschutz
    -0.77
    出版年
    -0.76
     ويكيميديا
    -0.75
     tablecloth
    -0.73
     مرئيه
    -0.71
     SqlCommand
    -0.70
     Motos
    -0.70
     compressors
    -0.68
     protoimpl
    -0.67
    POSITIVE LOGITS
    Hint
    3.25
    hint
    2.88
     hint
    2.80
     Hint
    2.80
     hints
    2.63
    HINT
    2.44
    Hints
    2.39
     Hints
    2.38
    hints
    2.33
     hinting
    1.68
    Activations Density 0.013%

    No Known Activations