© 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. 131
    Prev
    Next
    INDEX
    Explanations

    mentions of numbers, especially the number two or three

    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
     Nähe
    -0.68
    ποίη
    -0.64
     chrétiens
    -0.63
     traités
    -0.63
     alrededores
    -0.62
     vaisseaux
    -0.60
    layoutManager
    -0.60
     preuves
    -0.60
     Grecs
    -0.60
     οποίο
    -0.59
    POSITIVE LOGITS
     different
    1.18
     dozen
    0.96
     consecutive
    0.95
     separate
    0.93
     distinct
    0.92
    different
    0.85
     hundred
    0.79
     verschiedene
    0.79
     kinds
    0.78
     types
    0.76
    Activations Density 1.695%

    No Known Activations