© 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. 14004
    Prev
    Next
    INDEX
    Explanations

    references to specific software or applications related to Ubuntu

    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
    EDEFAULT
    -0.86
     Waray
    -0.83
    expandindo
    -0.82
    AddTagHelper
    -0.78
     avoient
    -0.78
     nawr
    -0.77
    ViewImports
    -0.73
    -------------</
    -0.72
     démocr
    -0.70
     étoient
    -0.69
    POSITIVE LOGITS
     comp
    0.44
     …
    0.41
     produ
    0.39
     interested
    0.39
     required
    0.38
    <eos>
    0.38
    jare
    0.38
    orship
    0.37
     induced
    0.37
    GeneratedMessage
    0.37
    Activations Density 0.003%

    No Known Activations