© 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. 3-RES-MATRYOSHKA-DC
    7. 1095
    Prev
    Next
    INDEX
    Explanations

    the word "wall" or words that include "wall"

    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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Neves
    -0.63
    Prat
    -0.63
    uoš
    -0.63
     ujednoznacz
    -0.59
     Plural
    -0.59
    Ofer
    -0.57
    Nib
    -0.56
    wpi
    -0.56
    הערות
    -0.55
    abase
    -0.55
    POSITIVE LOGITS
     wall
    3.50
    wall
    3.14
     Wall
    3.14
    Wall
    3.08
     WALL
    3.05
     walls
    3.02
    WALL
    2.86
     Walls
    2.75
    walls
    2.67
    Walls
    2.47
    Activations Density 0.118%

    No Known Activations