© 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. 17326
    Prev
    Next
    INDEX
    Explanations

    the presence of the letter 'y' in various 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
    SharedCtor
    -0.85
    RegressionTest
    -0.81
    IsMutable
    -0.80
    UnusedPrivate
    -0.78
    AutoScale
    -0.76
    AutoScaleMode
    -0.75
     tartalomajánló
    -0.73
    paravant
    -0.72
     виправивши
    -0.72
     للمعارف
    -0.71
    POSITIVE LOGITS
     Sist
    0.58
    си
    0.57
     Popis
    0.53
    array
    0.51
    famili
    0.50
    ir
    0.50
    moth
    0.50
     acquaintance
    0.50
     susi
    0.50
    ्य
    0.49
    Activations Density 0.000%

    No Known Activations