© 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. 2545
    Prev
    Next
    INDEX
    Explanations

    text discussing boosts, frames, axes, transformation, rotation, and other terms used in physics

    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
    AddTagHelper
    -0.83
    StoryboardSegue
    -0.74
    Autoritní
    -0.73
    MethodManager
    -0.62
    styleType
    -0.61
    tagHelperRunner
    -0.61
    المناصب
    -0.61
    sizeCache
    -0.60
    ValueStyle
    -0.59
    MigrationBuilder
    -0.59
    POSITIVE LOGITS
     frame
    1.18
     frames
    0.95
    Frame
    0.95
     Frame
    0.94
    frame
    0.93
     coordinate
    0.93
     FRAME
    0.88
     coordinates
    0.82
    frames
    0.80
     reference
    0.79
    Activations Density 0.335%

    No Known Activations