© 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. 1-RES-MATRYOSHKA-DC
    7. 30
    Prev
    Next
    INDEX
    Explanations

    occurrences of image-related terms associated with scanning, imaging, and visualization

    oai_token-act-pair · gpt-4.1-nano
    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
     @"/
    -0.71
    UnusedPrivate
    -0.66
    OGND
    -0.63
    InjectMocks
    -0.63
    PerformLayout
    -0.61
    Билгалдахарш
    -0.61
    exitRule
    -0.61
    __':
    -0.59
    GenerationType
    -0.59
    __':
    -0.56
    POSITIVE LOGITS
     image
    4.00
     Image
    3.64
     images
    3.58
    image
    3.48
    Image
    3.41
     Images
    3.27
     IMAGE
    3.22
    IMAGE
    2.98
    Images
    2.95
    images
    2.89
    Activations Density 2.681%

    No Known Activations