© 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. 20047
    Prev
    Next
    INDEX
    Explanations

    patterns related to complex relationships and dependencies in data or models

    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
    Coordonnées
    -0.44
     Judiciary
    -0.43
    Hozzáférés
    -0.42
    lccn
    -0.42
    Datuak
    -0.41
     téléphonique
    -0.41
    ardoor
    -0.41
     onOptions
    -0.40
    Identyfik
    -0.40
    ValueStyle
    -0.39
    POSITIVE LOGITS
     متعلقه
    0.76
    expandindo
    0.74
    Tembelea
    0.69
    ]")]
    0.65
     يتيمه
    0.59
    [::-
    0.59
    (©
    0.59
    CloseOperation
    0.58
    routeProvider
    0.57
    IMPORTED
    0.57
    Activations Density 0.404%

    No Known Activations