© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 453
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives and phrases indicating degrees of change or differentiation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     BoxDecoration
    -0.67
    ẠI
    -0.65
    rateful
    -0.63
    atissimo
    -0.63
    ❥
    -0.63
    Ỉ
    -0.62
    ändigt
    -0.60
    roppo
    -0.59
    ZIL
    -0.59
    icoot
    -0.59
    POSITIVE LOGITS
     than
    1.98
    than
    1.46
     THAN
    1.45
    Than
    1.40
     niż
    1.35
     easier
    1.27
     clearer
    1.27
     hơn
    1.24
     harder
    1.23
     safer
    1.23
    Activations Density 1.776%

    No Known Activations