© 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. 24-RES-MATRYOSHKA-DC
    7. 534
    Prev
    Next
    INDEX
    Explanations

    technical or scientific writing, especially emphasizing recent events and broad applicability across disciplines or uses.

    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.24.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.24.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
    ωμα
    -0.58
     eventuali
    -0.58
    IsMutable
    -0.57
    žete
    -0.57
    ieteur
    -0.55
    zką
    -0.55
    reportWebVitals
    -0.55
     sirup
    -0.54
    шти
    -0.53
    SPOILER
    -0.52
    POSITIVE LOGITS
     increasingly
    1.28
     increasing
    1.21
     trend
    1.19
     Increasing
    1.18
    increasing
    1.17
     growing
    1.16
    Increasing
    1.13
     trends
    1.12
     rapidly
    1.11
     advancements
    0.98
    Activations Density 1.863%

    No Known Activations