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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11870
    Prev
    Next
    INDEX
    Explanations

    pressure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tanooga
    -0.60
    jsii
    -0.57
     ویکی‌پدیا
    -0.57
     surla
    -0.56
    styleUrls
    -0.56
     BoxFit
    -0.56
     vouloir
    -0.55
    ngrx
    -0.54
     createSlice
    -0.54
    <bos>
    -0.53
    POSITIVE LOGITS
    دانشنامهٔ
    0.56
     glands
    0.55
     nuclei
    0.53
     Económica
    0.52
     melting
    0.52
     membranes
    0.52
    nias
    0.50
    cores
    0.49
     bars
    0.49
     grat
    0.47
    Activations Density 0.046%

    No Known Activations