© 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. 2313
    Prev
    Next
    INDEX
    Explanations

    variations on "core" and "Tre"

    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
     Efq
    -0.69
    rician
    -0.68
     jScrollPane
    -0.65
    yethylene
    -0.65
    DrawerToggle
    -0.64
     Sce
    -0.59
    addPreferredGap
    -0.58
    🏾
    -0.58
    ryl
    -0.58
    ska
    -0.58
    POSITIVE LOGITS
    search
    0.65
    ng
    0.53
    ns
    0.52
     createSlice
    0.52
     isInitialized
    0.52
     uren
    0.50
     ujednoznacz
    0.50
    na
    0.49
     Ore
    0.49
    Viited
    0.49
    Activations Density 0.184%

    No Known Activations