© 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. 1644
    Prev
    Next
    INDEX
    Explanations

    topic transitions or introductory phrases

    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
    шти
    -0.53
    zką
    -0.52
    tested
    -0.51
    agissait
    -0.50
    HKEY
    -0.48
    blon
    -0.47
     eventuali
    -0.46
    Spoiler
    -0.46
     violated
    -0.46
    liction
    -0.45
    POSITIVE LOGITS
     increasingly
    1.42
     Increasing
    1.41
    increasing
    1.38
    Increasing
    1.38
     increasing
    1.37
     advances
    1.30
     advancements
    1.27
     growing
    1.23
     technological
    1.15
     rapidly
    1.14
    Activations Density 2.453%

    No Known Activations