© 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. 46312
    Prev
    Next
    INDEX
    Explanations

    line

    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
    ThroughAttribute
    -0.97
    NameInMap
    -0.83
    GEBURTSDATUM
    -0.76
    webElementXpaths
    -0.70
    StructEnd
    -0.68
     disambiguazione
    -0.66
    line
    -0.63
     ProtoMessage
    -0.61
     line
    -0.59
     برانيه
    -0.59
    POSITIVE LOGITS
    createStatement
    0.62
    viewDidLoad
    0.61
    thyst
    0.53
     Sve
    0.52
     morire
    0.51
    __':
    0.49
     ContentValues
    0.49
    __))
    0.49
     صوتيه
    0.49
     htons
    0.48
    Activations Density 0.267%

    No Known Activations