© 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. 15628
    Prev
    Next
    INDEX
    Explanations

    specific letters and vowel-consonant patterns

    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
    IntoConstraints
    -1.04
    Попис
    -0.98
     nahilalakip
    -0.97
    WithIOException
    -0.95
     '\\;'
    -0.95
     Савезне
    -0.90
    RegressionTest
    -0.90
    MigrationBuilder
    -0.89
    aarrggbb
    -0.88
    PerformLayout
    -0.87
    POSITIVE LOGITS
     françaises
    0.48
    ets
    0.47
    vs
    0.46
    <
    0.44
     =
    0.44
    by
    0.43
    val
    0.42
    ins
    0.42
    ery
    0.42
    ke
    0.41
    Activations Density 0.013%

    No Known Activations