© 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. 12-RES-MATRYOSHKA-DC
    7. 1960
    Prev
    Next
    INDEX
    Explanations

    quantifiers and expressions of approximation

    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
     Weiden
    -0.57
     songs
    -0.55
    Songs
    -0.54
    𝘶
    -0.52
    iglio
    -0.51
     προβ
    -0.50
     fiind
    -0.50
    NgModule
    -0.49
    下が
    -0.49
    ゆ
    -0.49
    POSITIVE LOGITS
    Almost
    1.13
     nearly
    1.13
     Nearly
    1.13
     Almost
    1.12
     Casi
    1.07
    ctically
    1.07
    nearly
    1.06
    Casi
    1.06
    Nearly
    1.05
     almost
    1.04
    Activations Density 0.345%

    No Known Activations