© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14383
    Prev
    Next
    INDEX
    Explanations

    references to large or significant quantities or sizes

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.74
     spécialisé
    -0.61
     estekak
    -0.60
    RepeatedField
    -0.58
    makeConstraints
    -0.57
     noDo
    -0.57
    <()>
    -0.56
     linkovi
    -0.56
    NameInMap
    -0.55
     createSlice
    -0.53
    POSITIVE LOGITS
    subnet
    0.66
     subnet
    0.62
    Viki
    0.61
    andina
    0.59
    Subnet
    0.57
    ρύ
    0.55
    inci
    0.54
    issima
    0.53
    almaz
    0.53
    nextInt
    0.52
    Activations Density 0.258%

    No Known Activations