© 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. 233
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to scientific research papers

    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
    สือ
    -0.63
     tartalomajánló
    -0.61
    تفصیلات
    -0.59
    BeginContext
    -0.58
    atrième
    -0.56
    resave
    -0.55
    UnusedPrivate
    -0.54
    ibatis
    -0.54
    migrationBuilder
    -0.53
    rawDesc
    -0.53
    POSITIVE LOGITS
     size
    1.36
     location
    1.35
     characteristics
    1.31
     composition
    1.23
     nature
    1.20
     geography
    1.16
     shape
    1.13
     structure
    1.13
     type
    1.12
     configuration
    1.10
    Activations Density 5.201%

    No Known Activations