© 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. 2373
    Prev
    Next
    INDEX
    Explanations

    words related to measuring distance and communications tech

    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
    UseVisualStyle
    -0.59
    ----</
    -0.52
     resourceCulture
    -0.52
     autorytatywna
    -0.49
    änien
    -0.48
    ModelAdmin
    -0.47
    gypte
    -0.47
    Obrázky
    -0.46
    новништво
    -0.45
    eachtet
    -0.43
    POSITIVE LOGITS
     distance
    3.61
     Distance
    3.23
    distance
    3.14
     distances
    3.00
    Distance
    2.98
     DISTANCE
    2.81
     Distances
    2.61
     distancia
    2.58
    DISTANCE
    2.52
    distances
    2.41
    Activations Density 0.781%

    No Known Activations