© 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. 28579
    Prev
    Next
    INDEX
    Explanations

    statements related to evidence or demonstration of results

    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
     witness
    -0.44
    find
    -0.43
     contrary
    -0.39
    ॉग
    -0.39
    坎
    -0.38
    Witness
    -0.38
     vodou
    -0.38
     can
    -0.38
    can
    -0.38
    気が
    -0.37
    POSITIVE LOGITS
    expandindo
    1.13
    abestanden
    1.13
    Diweddarwch
    0.95
    RTLR
    0.91
     referenties
    0.90
    تقاوى
    0.89
     AssemblyCulture
    0.85
    Personendaten
    0.84
    twimg
    0.83
     calendriers
    0.81
    Activations Density 0.049%

    No Known Activations