© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 425
    Prev
    Next
    INDEX
    Explanations

    words generally associated with written stories or narrative arcs, plus a few related to technology

    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
    OGND
    -0.98
    polation
    -0.96
    beelding
    -0.93
    pecific
    -0.93
    MemoryWarning
    -0.90
    🏻‍♀️
    -0.88
    skosten
    -0.88
     AssemblyCompany
    -0.87
    upported
    -0.85
    kijken
    -0.84
    POSITIVE LOGITS
    -
    1.13
    w
    0.60
    bre
    0.59
    -/
    0.59
    bo
    0.57
    cu
    0.53
    k
    0.53
    ‐
    0.52
    post
    0.52
    bu
    0.52
    Activations Density 3.576%

    No Known Activations