© 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. 46329
    Prev
    Next
    INDEX
    Explanations

    HERE

    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
     Beecher
    -2.08
    neté
    -0.54
     kontin
    -0.50
     addSubview
    -0.49
    esModule
    -0.48
    swire
    -0.47
     BTN
    -0.45
    abay
    -0.44
    échal
    -0.44
    adays
    -0.43
    POSITIVE LOGITS
     صوتيه
    0.60
    WriteTagHelper
    0.57
     Normdatei
    0.57
    lgari
    0.55
    CORBA
    0.52
    TIMORE
    0.51
     ModelExpression
    0.50
    leos
    0.49
    SerializeField
    0.49
    ścioła
    0.48
    Activations Density 0.007%

    No Known Activations