© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13445
    Prev
    Next
    INDEX
    Explanations

    configuration settings related to view or plugin options

    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
    EndProject
    -0.79
    LLocation
    -0.77
    DataPropertyName
    -0.75
    TemporalType
    -0.74
    DeleteBehavior
    -0.74
    GenerationType
    -0.72
    sizeCache
    -0.71
    ⓧ
    -0.70
     difficulty
    -0.69
    UnusedPrivate
    -0.67
    POSITIVE LOGITS
    options
    1.92
    BorderFactory
    0.50
     Apalagi
    0.48
    Heres
    0.47
    itemView
    0.46
    masalah
    0.44
    ckeys
    0.44
    ops
    0.44
    begingroup
    0.43
    rophes
    0.43
    Activations Density 0.001%

    No Known Activations