© 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. 30942
    Prev
    Next
    INDEX
    Explanations

    structural patterns or hierarchies in data presentation

    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
    EndContext
    -0.80
     فريبيس
    -0.77
    SequentialGroup
    -0.75
     defaultstate
    -0.74
     оригіналу
    -0.72
    सन्दर्भ
    -0.71
    intios
    -0.69
    "](
    -0.66
     lenker
    -0.66
    Geplaatst
    -0.65
    POSITIVE LOGITS
     competitivo
    0.47
     dimaksud
    0.46
     raiſ
    0.44
    стъ
    0.43
    FetchType
    0.43
     nélkül
    0.43
    toni
    0.42
    pl
    0.42
     (
    0.41
     ſhe
    0.41
    Activations Density 0.023%

    No Known Activations