© 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. 20544
    Prev
    Next
    INDEX
    Explanations

    mathematical proofs or formal statements

    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
    Negative Logits
    OGND
    -0.56
    AMAHA
    -0.55
    󠁢
    -0.53
    star
    -0.51
     Pia
    -0.51
    phrine
    -0.49
    roc
    -0.49
    ✨:
    -0.49
     Sienna
    -0.49
    tellen
    -0.49
    POSITIVE LOGITS
    ----</
    0.79
     חיצוניים
    0.72
     дописавши
    0.71
    Lähteet
    0.69
     IBOutlet
    0.68
    Erreferentziak
    0.66
     >=",
    0.65
    WebElementEntity
    0.63
     समीक्षक
    0.61
     estekak
    0.60
    Activations Density 0.009%

    No Known Activations