© 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. 12147
    Prev
    Next
    INDEX
    Explanations

    references to error messages and logging outputs

    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
    <strong>
    -0.68
    <em>
    -0.63
    </h4>
    -0.60
    <u>
    -0.60
    </strong>
    -0.59
     (
    -0.59
    op
    -0.58
    3
    -0.58
    9
    -0.56
     P
    -0.56
    POSITIVE LOGITS
     stdout
    1.46
    stderr
    1.38
    stdout
    1.34
     stderr
    1.30
    Stderr
    1.19
     stdin
    1.04
    DOUT
    0.98
    Stdout
    0.94
     doubtnut
    0.93
     Wiktionnaire
    0.92
    Activations Density 0.003%

    No Known Activations