© 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. 26135
    Prev
    Next
    INDEX
    Explanations

    references to specific configurations and settings in technical or scientific 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
    InputBorder
    -0.76
    CodeAttribute
    -0.74
    oredCriteria
    -0.72
    ThroughAttribute
    -0.69
    ruptedException
    -0.69
    GEBURTSDATUM
    -0.69
     whereof
    -0.68
     resourceCulture
    -0.68
    AsUp
    -0.67
    PMailer
    -0.67
    POSITIVE LOGITS
    ✨:
    0.54
     Fe
    0.44
    setColor
    0.42
     исто
    0.42
     Sa
    0.42
     BoxFit
    0.42
    Kaynakça
    0.40
     sie
    0.40
    ober
    0.39
     Cas
    0.39
    Activations Density 0.336%

    No Known Activations