© 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. 6-RES-MATRYOSHKA-DC
    7. 1295
    Prev
    Next
    INDEX
    Explanations

    HTML relating to website navigation

    oai_token-act-pair · gemini-2.0-flash
    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
     gyhoeddwyd
    -0.76
     CascadeType
    -0.71
     FetchType
    -0.71
    ItemBackground
    -0.68
    انيف
    -0.67
     gawas
    -0.66
    CodedInputStream
    -0.66
     EdgeInsets
    -0.65
     CWE
    -0.64
    CWE
    -0.64
    POSITIVE LOGITS
    лья
    0.59
     Henley
    0.56
    engue
    0.55
    cipe
    0.54
    _"+
    0.53
     Mig
    0.53
    \_
    0.52
    ViewFeatures
    0.52
    ="
    0.51
    SequentialGroup
    0.50
    Activations Density 0.108%

    No Known Activations