© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 199
    Prev
    Next
    INDEX
    Explanations

    continuing statements

    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
    Embeddable
    -0.60
    who
    -0.52
    closePath
    -0.52
    how
    -0.50
     conducta
    -0.50
     Beispiel
    -0.49
     tức
    -0.49
     väx
    -0.49
    ydon
    -0.48
    째
    -0.48
    POSITIVE LOGITS
    Clik
    0.70
     BoxFit
    0.64
    XmlAccessType
    0.63
    webElementXpaths
    0.61
    Revenir
    0.61
     noqa
    0.60
    Espèce
    0.59
    ChildScrollView
    0.58
    tagHelperRunner
    0.56
    TargetException
    0.54
    Activations Density 0.001%

    No Known Activations