© 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. 6-RES-MATRYOSHKA-DC
    7. 494
    Prev
    Next
    INDEX
    Explanations

    the word "type" followed by a value

    oai_token-act-pair · gemini-2.0-flash
    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
    UnsafeEnabled
    -0.82
     AppBar
    -0.75
    ImageField
    -0.71
     Pease
    -0.69
    ่ว
    -0.65
     remo
    -0.62
     cumin
    -0.62
     Carrots
    -0.62
     JMenuItem
    -0.61
     McCullough
    -0.61
    POSITIVE LOGITS
     Type
    1.99
     TYPE
    1.96
     type
    1.88
     types
    1.79
    type
    1.73
    TYPE
    1.71
     getType
    1.71
    Type
    1.66
     Types
    1.63
    types
    1.62
    Activations Density 1.102%

    No Known Activations