© 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. 14392
    Prev
    Next
    INDEX
    Explanations

    dashes or other symbols to indicate organization or separation in data presentation

    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
    Datuak
    -0.73
    MessageTagHelper
    -0.70
    extAlignment
    -0.69
    AnchorStyles
    -0.65
    dflare
    -0.65
     שוליים
    -0.63
    DoubleQuotes
    -0.62
    classnames
    -0.61
     classNames
    -0.60
    ftagPool
    -0.59
    POSITIVE LOGITS
     AssemblyVersion
    0.56
     AttributeSet
    0.56
     Olympus
    0.55
     Ejecutivo
    0.55
    enumii
    0.53
    нитар
    0.52
    __":
    0.52
    labus
    0.52
    fficio
    0.50
    Rasp
    0.49
    Activations Density 0.021%

    No Known Activations