© 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. 18-RES-MATRYOSHKA-DC
    7. 447
    Prev
    Next
    INDEX
    Explanations

    the word "method," especially within the context of technical writing or documentation

    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.18.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.18.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
    WireFormatLite
    -0.66
     ExecuteAsync
    -0.65
    WebControls
    -0.65
     onCreateView
    -0.57
     createSlice
    -0.57
     Turf
    -0.56
    DataSnapshot
    -0.56
     onCancelled
    -0.55
     flotation
    -0.55
     Immunity
    -0.55
    POSITIVE LOGITS
    ologically
    0.77
    methods
    0.77
     Methods
    0.75
     methods
    0.74
    __":
    0.69
    ologies
    0.67
    Methods
    0.66
     Method
    0.65
     Manner
    0.65
     METHOD
    0.64
    Activations Density 0.946%

    No Known Activations