© 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. 18-RES-MATRYOSHKA-DC
    7. 188
    Prev
    Next
    INDEX
    Explanations

    words related to orientation, direction, and vectors

    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.18.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.18.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
     bare
    -0.48
    StackSize
    -0.44
     Thin
    -0.43
    acze
    -0.43
     gants
    -0.41
     nit
    -0.40
     late
    -0.40
     exemption
    -0.40
     exempt
    -0.39
     Threshold
    -0.39
    POSITIVE LOGITS
     direction
    1.43
    direction
    1.18
     orientation
    1.16
     Direction
    1.16
     directions
    1.15
     DIRECTION
    1.12
    Direction
    1.11
    orientation
    1.03
     perpendicular
    1.02
    方向
    1.02
    Activations Density 4.431%

    No Known Activations