© 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. 2219
    Prev
    Next
    INDEX
    Explanations

    scientific writing that mentions direction, orientation along an axis, or planes

    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
     angle
    -0.88
     Angle
    -0.86
     ANGLE
    -0.81
     angles
    -0.79
     ostavi
    -0.78
    awtextra
    -0.76
    Angle
    -0.75
    angle
    -0.75
    :✨
    -0.75
     viewType
    -0.71
    POSITIVE LOGITS
     axis
    0.72
     axes
    0.68
    colorbar
    0.57
    axis
    0.57
    Axis
    0.54
     eixo
    0.53
    zewod
    0.53
    AccessFile
    0.53
     Axes
    0.53
     directions
    0.52
    Activations Density 0.114%

    No Known Activations