© 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. 1369
    Prev
    Next
    INDEX
    Explanations

    phrases indicating duration or frequency related to "over."

    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
    findElement
    -0.90
    Portail
    -0.86
    ="{{$
    -0.81
    Fixtures
    -0.78
     Diab
    -0.77
    annica
    -0.73
    ✨:
    -0.72
     Briggs
    -0.71
     Lindgren
    -0.69
    {{$
    -0.69
    POSITIVE LOGITS
     OVER
    1.59
     Over
    1.56
     over
    1.55
    over
    1.55
    Over
    1.52
    OVER
    1.38
     Overs
    1.30
     Overton
    1.23
    overs
    1.16
    Overs
    1.14
    Activations Density 0.610%

    No Known Activations