© 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. 22-RES-MATRYOSHKA-DC
    7. 829
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "to" preceded by various words, often verbs

    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/blocks.22.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.22.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
     volon
    -0.50
     malah
    -0.49
    instancetype
    -0.47
     never
    -0.45
     niemals
    -0.44
     gewünschten
    -0.44
     tranquila
    -0.44
     easily
    -0.43
     chỉ
    -0.43
    Melhor
    -0.43
    POSITIVE LOGITS
     necessariamente
    0.94
     necesariamente
    0.88
     contend
    0.84
     ComVisible
    0.83
     HasFactory
    0.79
    FunctionFlags
    0.76
     Wikimedijinoj
    0.73
    JMenuBar
    0.72
    PerformLayout
    0.71
     ujednoznacz
    0.70
    Activations Density 0.315%

    No Known Activations