© 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. 23057
    Prev
    Next
    INDEX
    Explanations

    structured data elements within a document

    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
     שוליים
    -1.06
    expandindo
    -1.02
    RuleContext
    -0.98
     SwitchCompat
    -0.98
     propOrder
    -0.98
    __((
    -0.95
    TypedDataSet
    -0.90
    ">//
    -0.90
    Atsauces
    -0.90
     Мексичка
    -0.88
    POSITIVE LOGITS
    ever
    0.53
    -
    0.53
    ver
    0.51
    Ever
    0.51
     Coffey
    0.51
     lenger
    0.51
    ane
    0.49
    </em>
    0.49
     anti
    0.47
    amen
    0.46
    Activations Density 0.021%

    No Known Activations