© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 29954
    Prev
    Next
    INDEX
    Explanations

    the word "expression" in scientific text

    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
    Express
    -1.08
    express
    -1.07
     EXPRESS
    -1.03
     express
    -0.97
     Express
    -0.93
     expressed
    -0.92
     expresses
    -0.85
     expresa
    -0.84
    EXPRESS
    -0.83
     expressing
    -0.82
    POSITIVE LOGITS
    LookAnd
    0.82
    yntaxException
    0.68
    WithIOException
    0.63
    #+#
    0.62
    InputLabel
    0.61
    IntoConstraints
    0.60
    expandindo
    0.57
     LAYER
    0.57
    einf
    0.57
    TRAILING
    0.56
    Activations Density 0.015%

    No Known Activations