© 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. 20855
    Prev
    Next
    INDEX
    Explanations

    nested parentheses and brackets

    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
     '{@
    -0.59
     ligiloj
    -0.57
     gi
    -0.55
     kem
    -0.54
     Kem
    -0.54
     آم
    -0.54
    evos
    -0.54
    gor
    -0.52
    mero
    -0.52
     tee
    -0.51
    POSITIVE LOGITS
     Sitten
    0.73
    ()");
    0.71
    modb
    0.71
     Pilate
    0.71
     Tivoli
    0.70
     |]
    0.69
     
    0.68
     Cæsar
    0.68
     Eud
    0.67
     ?",
    0.66
    Activations Density 0.037%

    No Known Activations