© 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. 14642
    Prev
    Next
    INDEX
    Explanations

    terms related to plans and planning processes

    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
     cuch
    -0.72
    asure
    -0.70
    cheduling
    -0.69
     erd
    -0.68
    ẤT
    -0.66
    ionage
    -0.66
     scheduling
    -0.65
    Viel
    -0.65
     rescheduled
    -0.65
    Gare
    -0.65
    POSITIVE LOGITS
     doInBackground
    0.87
    mergeFrom
    0.74
     newBuilder
    0.73
    makeConstraints
    0.70
    yntaxException
    0.70
    RTEX
    0.69
     /\.
    0.69
     PeEnEo
    0.68
    @[+][
    0.68
     وتسجيلات
    0.66
    Activations Density 0.012%

    No Known Activations