© 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. 24-RES-MATRYOSHKA-DC
    7. 1413
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and symbols used in mathematical or scientific expressions, sometimes including exponents and subscripts

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    FFFF
    -0.54
    OOOOOOOO
    -0.53
     FID
    -0.52
     EEPROM
    -0.52
     Damien
    -0.50
    UnusedPrivate
    -0.50
     Frie
    -0.48
     ADO
    -0.48
     Alamofire
    -0.48
    UUUU
    -0.47
    POSITIVE LOGITS
    anyahu
    0.63
    Produzione
    0.59
    protoimpl
    0.59
     Normdatei
    0.58
    ftagPool
    0.58
    InitVars
    0.57
    IsMutable
    0.57
     Jr
    0.57
    InjectAttribute
    0.56
    Xna
    0.56
    Activations Density 2.485%

    No Known Activations