Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 30434
    Prev
    Next
    INDEX
    Explanations

    the word "wet" and related words

    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
    bootstrapcdn
    -0.96
    ########.
    -0.84
     Theron
    -0.84
     lccn
    -0.79
    DeleteMapping
    -0.76
    Hentet
    -0.75
    Datuak
    -0.75
     виправивши
    -0.75
    urar
    -0.74
    fulness
    -0.72
    POSITIVE LOGITS
    Wet
    1.30
     wet
    1.29
     Wet
    1.23
     WET
    1.23
    WET
    1.20
    wet
    1.19
     wetting
    0.91
     wetter
    0.76
     Wetlands
    0.70
    湿
    0.69
    Activations Density 0.004%

    No Known Activations