© 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. 0-CLT-HP
    7. 43823
    Prev
    Next
    INDEX
    Explanations

    ventilator

    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
     démocr
    -0.55
     hanem
    -0.53
    })));
    -0.53
     lccn
    -0.52
     Waray
    -0.52
    Портал
    -0.52
    Brigitte
    -0.51
    **
    -0.50
     ebook
    -0.48
     eBook
    -0.48
    POSITIVE LOGITS
    providedIn
    0.69
    washed
    0.63
    UniformLocation
    0.60
     defStyle
    0.58
    flashdata
    0.57
    MessageDigest
    0.57
    wash
    0.55
    windowFixed
    0.55
    pane
    0.55
    house
    0.54
    Activations Density 0.104%

    No Known Activations