© 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. 0-RES-MATRYOSHKA-DC
    7. 11250
    Prev
    Next
    INDEX
    Explanations

    references to image-related terms, especially those involving image loading or processing

    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
    Composable
    -0.58
    صبحت
    -0.52
    Portail
    -0.52
    Derbyniad
    -0.52
    stums
    -0.51
     instrument
    -0.51
    StructEnd
    -0.51
    CreateIndex
    -0.50
    \"");
    -0.50
    酎
    -0.49
    POSITIVE LOGITS
    Image
    1.77
     Image
    0.90
    GenerationType
    0.79
    bootstrapcdn
    0.65
    Imagen
    0.64
     Interestingly
    0.60
    ImageList
    0.60
    laufen
    0.59
    őben
    0.59
    Interestingly
    0.58
    Activations Density 0.002%

    No Known Activations