© 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. 20722
    Prev
    Next
    INDEX
    Explanations

    specific identifiers and references within structured data

    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
    expandindo
    -0.96
    AndEndTag
    -0.79
    دانشنامهٔ
    -0.74
     ?>/
    -0.73
     препратки
    -0.71
     Theſe
    -0.69
    KommentareTeilen
    -0.68
     Efq
    -0.68
    OGND
    -0.67
    EndContext
    -0.66
    POSITIVE LOGITS
    thias
    0.43
    Scheduled
    0.41
    velle
    0.40
     En
    0.40
    Datetime
    0.39
     group
    0.39
     gere
    0.39
     branch
    0.39
     شه
    0.39
    מה
    0.38
    Activations Density 0.160%

    No Known Activations