© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19234
    Prev
    Next
    INDEX
    Explanations

    numerical data or figures

    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
    pitaux
    -0.68
     Réponses
    -0.61
     eccell
    -0.59
     alpin
    -0.58
     Huguen
    -0.57
     apic
    -0.56
    zieży
    -0.56
     zirc
    -0.56
     Grafton
    -0.56
     Chartres
    -0.55
    POSITIVE LOGITS
    SequentialGroup
    0.66
    mendation
    0.65
    rungsseite
    0.65
    Pranala
    0.65
    ferrer
    0.64
    ajuato
    0.61
    ⓧ
    0.60
     OFDb
    0.60
    RegressionTest
    0.58
    curité
    0.57
    Activations Density 0.026%

    No Known Activations