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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 3301
    Prev
    Next
    INDEX
    Explanations

    references to supplementary or additional information

    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
     supérieures
    -0.61
     majeurs
    -0.57
     spad
    -0.57
     Kell
    -0.56
     llaves
    -0.56
     BOMB
    -0.56
     Harts
    -0.56
    IsNullOrEmpty
    -0.55
     hoja
    -0.55
     Millar
    -0.55
    POSITIVE LOGITS
    Additional
    0.91
     *)__
    0.85
     Additional
    0.82
    ADDITIONAL
    0.82
    rungsseite
    0.79
     ――――――――
    0.79
    antaine
    0.77
    transQ
    0.76
    pædia
    0.75
    vábbi
    0.74
    Activations Density 0.030%

    No Known Activations