© 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. 32074
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation used in programming or data analysis contexts

    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
    IMPORTED
    -0.56
    forRoot
    -0.52
     dentelle
    -0.50
    võ
    -0.50
    JdbcTemplate
    -0.49
    leukin
    -0.48
    CORBA
    -0.48
     Preferencias
    -0.48
     Αγ
    -0.47
     flocc
    -0.47
    POSITIVE LOGITS
    aarrggbb
    0.63
    Pautan
    0.63
     '\\;'
    0.63
     ProtoMessage
    0.62
     EClass
    0.59
    ########.
    0.58
    ształ
    0.56
     فريبيس
    0.54
     jScrollPane
    0.53
    ässig
    0.53
    Activations Density 0.289%

    No Known Activations