© 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. 17162
    Prev
    Next
    INDEX
    Explanations

    phrases and numbers related to quantity or frequency

    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
    ">//
    -0.44
     speciale
    -0.44
     very
    -0.43
     selve
    -0.43
    ...
    -0.42
    ruptedException
    -0.42
     ό
    -0.42
    retmen
    -0.41
     colourful
    -0.41
    abadi
    -0.41
    POSITIVE LOGITS
    Datuak
    0.89
    WireFormat
    0.88
     consultato
    0.75
     protoimpl
    0.75
     BoxDecoration
    0.74
     समीक्षक
    0.74
    enumi
    0.73
     iprot
    0.71
    клопе
    0.70
    +#+
    0.69
    Activations Density 0.056%

    No Known Activations