© 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. 21047
    Prev
    Next
    INDEX
    Explanations

    references to additional information or resources

    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
    SequentialGroup
    -0.72
    вгений
    -0.68
     وتسجيلات
    -0.66
    romechanical
    -0.66
    angering
    -0.64
     Efq
    -0.62
     ';
    -0.61
    ">—
    -0.60
     poffe
    -0.60
     Monfieur
    -0.59
    POSITIVE LOGITS
    Джерела
    0.59
    Bronnen
    0.56
    MessageInfo
    0.56
     Drapeau
    0.54
     resourceCulture
    0.51
    JsonProperty
    0.50
    ApiModel
    0.50
    InitVars
    0.49
    তথ্যসূত্র
    0.48
     about
    0.48
    Activations Density 0.015%

    No Known Activations