© 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. 24391
    Prev
    Next
    INDEX
    Explanations

    numeric values associated with configuration parameters in a technical or programming context

    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
     Theory
    -0.53
    Theory
    -0.53
     Bark
    -0.51
    mak
    -0.50
     Ank
    -0.48
     Ne
    -0.47
     typelib
    -0.47
     Cec
    -0.47
     /\.
    -0.47
     theory
    -0.47
    POSITIVE LOGITS
     Debussy
    0.69
    الدراسه
    0.66
     stanzas
    0.66
    UnknownFields
    0.65
    Mustard
    0.65
    fordshire
    0.65
     Allahabad
    0.65
    rsiniz
    0.64
     Wikisource
    0.64
    insegna
    0.64
    Activations Density 0.042%

    No Known Activations