© 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. 22-RES-MATRYOSHKA-DC
    7. 514
    Prev
    Next
    INDEX
    Explanations

    numerical ranges

    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
     mesmas
    -0.55
     otomatig
    -0.52
     yeux
    -0.50
    олові
    -0.49
    maxsize
    -0.47
    ณะ
    -0.47
    uegos
    -0.46
    ∬
    -0.45
     arşivlendi
    -0.45
    pozorn
    -0.45
    POSITIVE LOGITS
     range
    2.36
     Range
    2.03
    range
    2.03
     ranges
    2.02
    Range
    1.96
     ranging
    1.94
     RANGE
    1.90
    RANGE
    1.73
     ranged
    1.73
     Ranges
    1.71
    Activations Density 1.595%

    No Known Activations