© 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. 12217
    Prev
    Next
    INDEX
    Explanations

    repeated patterns of characters

    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
    Not in Any Lists

    No Comments

    Negative Logits
     localObject
    -0.55
     existi
    -0.46
     procede
    -0.46
    IntoConstraints
    -0.46
     liga
    -0.44
    یکی
    -0.44
    SourceChecksum
    -0.43
    يميديا
    -0.43
    談社
    -0.43
    igem
    -0.42
    POSITIVE LOGITS
     Efq
    1.00
     Houſe
    0.85
     Majefty
    0.84
     Reſ
    0.84
     blz
    0.80
     Anſ
    0.79
     ſeveral
    0.77
    RTEX
    0.76
    __':
    0.75
     Diſ
    0.75
    Activations Density 0.003%

    No Known Activations