© 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. 20494
    Prev
    Next
    INDEX
    Explanations

    references to lists of media or news channels

    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
    bootstrapcdn
    -0.58
    tonsoft
    -0.52
    età
    -0.48
     preds
    -0.45
    ssa
    -0.44
     errorCode
    -0.42
     edad
    -0.42
    إنه
    -0.42
     wind
    -0.41
     cut
    -0.41
    POSITIVE LOGITS
    بوابة
    0.72
    providedIn
    0.72
     defaultstate
    0.65
    tamol
    0.63
    าสตร์
    0.63
    GraphicsUnit
    0.60
     distanciation
    0.60
     jLabel
    0.59
     beginnetje
    0.57
    jmniej
    0.56
    Activations Density 0.024%

    No Known Activations