© 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. 14579
    Prev
    Next
    INDEX
    Explanations

    statistical properties and conditions related to probability distributions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -0.52
    جغرافيا
    -0.52
     yourself
    -0.51
    ülen
    -0.50
     nhắc
    -0.50
     Chré
    -0.50
    ATEN
    -0.48
    []"
    -0.48
     veracity
    -0.48
    णा
    -0.47
    POSITIVE LOGITS
     transfieras
    0.79
    Personensuche
    0.72
     ihren
    0.71
     its
    0.63
     صوتيه
    0.63
     الرياضيه
    0.62
    tvguidetime
    0.59
     Walkover
    0.59
     duquel
    0.56
     their
    0.56
    Activations Density 1.115%

    No Known Activations