© 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. 4-CLT-HP
    7. 2171
    Prev
    Next
    INDEX
    Explanations

    indication/suggestion

    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
    ConstraintMaker
    -0.63
    principalColumn
    -0.62
     Вікі
    -0.59
    moveToFirst
    -0.57
    httphttps
    -0.57
     فريبيس
    -0.57
     Chwiliwch
    -0.56
    슷
    -0.55
    XmlRootElement
    -0.55
    resave
    -0.55
    POSITIVE LOGITS
     that
    0.66
     possible
    0.65
    XmlAccessType
    0.59
     possibles
    0.55
     this
    0.54
    osho
    0.52
    ésia
    0.52
     the
    0.52
     a
    0.50
    photobucket
    0.49
    Activations Density 0.005%

    No Known Activations