© 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. 3-RES-MATRYOSHKA-DC
    7. 250
    Prev
    Next
    INDEX
    Explanations

    the attribute "type" and associated characters

    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
    -0.94
     AppBar
    -0.75
     HomeComponent
    -0.75
     ganglia
    -0.70
     DialogInterface
    -0.70
     fossa
    -0.68
     heapq
    -0.68
     nukes
    -0.68
    ceuticals
    -0.67
     nicio
    -0.67
    POSITIVE LOGITS
     type
    2.91
     Type
    2.78
    type
    2.67
     TYPE
    2.63
    Type
    2.48
     types
    2.44
    TYPE
    2.39
     tipo
    2.27
    types
    2.19
     Types
    2.14
    Activations Density 1.158%

    No Known Activations