© 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. 22-RES-MATRYOSHKA-DC
    7. 2483
    Prev
    Next
    INDEX
    Explanations

    sentences discussing the biological nanoscale

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     muß
    -1.13
     daß
    -1.03
     läßt
    -0.99
     idéia
    -0.97
    faßt
    -0.82
     Schluß
    -0.77
     Надо
    -0.75
     Einfluß
    -0.73
     biß
    -0.73
    것은
    -0.68
    POSITIVE LOGITS
     onboarding
    0.86
     incentiv
    0.85
     leveraging
    0.85
     Notably
    0.84
     impactful
    0.83
     seamlessly
    0.82
     functionalities
    0.81
     upfront
    0.81
     lenker
    0.80
     aligns
    0.78
    Activations Density 1.763%

    No Known Activations