© 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. 41059
    Prev
    Next
    INDEX
    Explanations

    Pam/Virgin

    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
     pamp
    -0.97
    GEBURTSDATUM
    -0.91
    Personensuche
    -0.79
    Personendaten
    -0.79
    parsedMessage
    -0.78
     Virgin
    -0.75
     Италијани
    -0.75
    WriteBarrier
    -0.74
     Pamp
    -0.70
     otomatig
    -0.69
    POSITIVE LOGITS
    as
    0.66
    TagMode
    0.54
    AS
    0.52
     Mar
    0.50
    As
    0.47
    asam
    0.47
    aski
    0.46
     unit
    0.44
    Mar
    0.42
    asha
    0.42
    Activations Density 0.013%

    No Known Activations