© 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. 5-CLT-HP
    7. 2922
    Prev
    Next
    INDEX
    Explanations

    Getty

    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
    +#+#
    -0.68
    verwijspagina
    -0.66
    ArrowToggle
    -0.58
     Roskov
    -0.54
    WithIOException
    -0.53
    GEBURTSDATUM
    -0.53
    providedIn
    -0.51
    #+#
    -0.51
    rungsseite
    -0.50
     kaarangay
    -0.48
    POSITIVE LOGITS
    styleable
    0.64
    matchCondition
    0.62
    ArgumentParser
    0.57
     Found
    0.56
    Clik
    0.54
     ISSUED
    0.54
    cripciones
    0.52
    ositol
    0.52
     noqa
    0.51
    TestingModule
    0.51
    Activations Density 0.055%

    No Known Activations