© 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. 2-RES-MATRYOSHKA-DC
    7. 3675
    Prev
    Next
    INDEX
    Explanations

    instances of the word "flat" in text

    oai_token-act-pair · gpt-4.1-nano
    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
    참고
    -0.63
    ArgsConstructor
    -0.63
    ArgumentParser
    -0.58
    Gweler
    -0.58
    restes
    -0.58
     MainAxisSize
    -0.56
    @+
    -0.56
    دانشنامهٔ
    -0.56
     ocu
    -0.55
    XmlRootElement
    -0.55
    POSITIVE LOGITS
     flat
    3.78
    flat
    3.56
     Flat
    3.44
    Flat
    3.41
     FLAT
    3.25
    FLAT
    3.02
     flats
    2.63
     flatter
    2.39
    flats
    2.34
     flattened
    2.22
    Activations Density 0.011%

    No Known Activations