© 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. 22-RES-MATRYOSHKA-DC
    7. 2933
    Prev
    Next
    INDEX
    Explanations

    the word "short" and common words near it like "term" and "and"

    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.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.64
     newBuilder
    -0.63
     overdue
    -0.62
     lon
    -0.60
     lentement
    -0.58
    LLocation
    -0.57
    slowly
    -0.57
    "}")
    -0.57
    typeorm
    -0.56
    ofire
    -0.56
    POSITIVE LOGITS
     SHORT
    0.91
     Short
    0.90
    Short
    0.89
     short
    0.87
    SHORT
    0.83
     Shorts
    0.81
    short
    0.71
    ened
    0.70
    coming
    0.69
    Shorts
    0.68
    Activations Density 0.070%

    No Known Activations