© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 26933
    Prev
    Next
    INDEX
    Explanations

    statistical measurements and values in scientific contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    évaluateur
    -0.77
    parsedMessage
    -0.71
    
    -0.67
     समीक्षक
    -0.66
    醐
    -0.63
     prochains
    -0.62
     prismatic
    -0.62
     חיצוניים
    -0.60
     Wikimedijinoj
    -0.60
    principalColumn
    -0.60
    POSITIVE LOGITS
    EndContext
    0.54
    AfterClass
    0.47
    CONCURRENT
    0.45
    FFE
    0.44
    attamento
    0.42
    као
    0.42
    хал
    0.42
    ьаж
    0.42
     nan
    0.41
    Proses
    0.41
    Activations Density 0.001%

    No Known Activations