© 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. 14021
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating differences in measurements or quantities

    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
    IndentedString
    -0.66
     AssemblyCompany
    -0.63
     للاسماء
    -0.63
     Coim
    -0.59
    sidemargin
    -0.59
    Rohy
    -0.58
     насељу
    -0.57
    ⓘ
    -0.55
     invokingState
    -0.54
    Šaltiniai
    -0.54
    POSITIVE LOGITS
     møte
    0.57
     Nobel
    0.57
     natten
    0.54
    zunehmen
    0.51
     supérieures
    0.51
     بيها
    0.50
     Độ
    0.50
     része
    0.50
     الرغم
    0.50
     Erwartungen
    0.48
    Activations Density 0.019%

    No Known Activations