© 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. 23375
    Prev
    Next
    INDEX
    Explanations

    dates and deadlines for submissions

    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
     indisponible
    -0.64
    RTSC
    -0.60
    mazoo
    -0.59
     للمعارف
    -0.55
     poffible
    -0.52
    oa̍t
    -0.50
    SequentialGroup
    -0.50
    Démographie
    -0.50
     moeilijk
    -0.50
    __":
    -0.49
    POSITIVE LOGITS
    tedt
    0.67
    istoitu
    0.62
    AsStream
    0.60
    twimg
    0.54
    ScopeManager
    0.53
    labelledby
    0.53
    脚注の使い方
    0.53
    Chham
    0.51
    StandardCharsets
    0.51
    onymes
    0.50
    Activations Density 0.010%

    No Known Activations