© 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. 31811
    Prev
    Next
    INDEX
    Explanations

    binary truth values and their corresponding labels

    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
    batore
    -0.65
    évaluateur
    -0.63
    rrggbb
    -0.61
     shown
    -0.58
    bricht
    -0.57
    Składniki
    -0.57
     plupart
    -0.54
     itſelf
    -0.54
     tph
    -0.54
     SSSR
    -0.54
    POSITIVE LOGITS
     ***!
    0.78
    MLLoader
    0.65
    hoeddwyd
    0.59
    issus
    0.57
    FXML
    0.57
    Vers
    0.53
    verwijspagina
    0.51
     nahilalakip
    0.51
    LookAnd
    0.51
     Normdatei
    0.49
    Activations Density 0.010%

    No Known Activations