© 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. 397
    Prev
    Next
    INDEX
    Explanations

    the word "the" followed by a word that begins with a consonant unless "the" starts a paragraph and find article references

    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
    AddTagHelper
    -0.57
    only
    -0.54
    Rüyada
    -0.52
    ONLY
    -0.51
    expandindo
    -0.50
    very
    -0.50
    団
    -0.48
    untuk
    -0.47
     nation
    -0.47
    muy
    -0.46
    POSITIVE LOGITS
     mentioned
    0.81
    onAttach
    0.80
     obtained
    0.79
     above
    0.75
     observed
    0.75
     investigated
    0.75
     experimentally
    0.74
    SharedDtor
    0.74
    WriteBarrier
    0.71
     analyzed
    0.71
    Activations Density 2.140%

    No Known Activations