© 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. 10792
    Prev
    Next
    INDEX
    Explanations

    terms related to non-canonical or non-standard definitions

    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
     виправивши
    -0.85
     متعلقه
    -0.76
     utafitiHapana
    -0.75
     ProtoMessage
    -0.74
    aarrggbb
    -0.73
     دیکھیے
    -0.72
    IVEREF
    -0.70
    tvguidetime
    -0.70
    providedIn
    -0.69
     Мексичка
    -0.69
    POSITIVE LOGITS
    bParam
    0.66
    NegativeButton
    0.64
     koni
    0.63
    Patent
    0.57
     incontinence
    0.52
    erover
    0.51
    Norton
    0.51
     alpaca
    0.50
     Baptists
    0.50
     fendi
    0.50
    Activations Density 0.021%

    No Known Activations