© 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. 25553
    Prev
    Next
    INDEX
    Explanations

    conjunctions and prepositions typically used in legal or software-related documentation

    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
    клопе
    -0.56
    gies
    -0.54
    lyse
    -0.52
     InputDecoration
    -0.52
    FormUrlEncoded
    -0.50
    lime
    -0.49
     typelib
    -0.49
    garet
    -0.49
    oinette
    -0.47
    meteries
    -0.47
    POSITIVE LOGITS
    ISupport
    0.76
    MemoryWarning
    0.65
    __*/
    0.65
    KommentareTeilen
    0.60
    
    0.59
    ReusableCell
    0.58
     terminée
    0.57
     Riproduzione
    0.56
    最快更新
    0.55
     troubled
    0.54
    Activations Density 0.002%

    No Known Activations