© 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. 15892
    Prev
    Next
    INDEX
    Explanations

    dimensions or measurements related to objects

    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
    djangoproject
    -0.76
    بوابة
    -0.68
    TagMode
    -0.62
    MigrationBuilder
    -0.57
     veau
    -0.57
    äre
    -0.54
     lettura
    -0.53
     aient
    -0.52
    Portail
    -0.52
    alnız
    -0.52
    POSITIVE LOGITS
    soort
    0.74
     viewType
    0.65
     esternos
    0.63
     صوتيه
    0.62
    urlopen
    0.62
     تانيه
    0.61
    balleur
    0.61
    tonode
    0.60
    TypedDataSet
    0.59
    withIdentifier
    0.59
    Activations Density 0.014%

    No Known Activations