© 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. 5-CLT-HP
    7. 860
    Prev
    Next
    INDEX
    Explanations

    "The" and asterisks

    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
     مرئيه
    -0.71
    NameInMap
    -0.69
    AndEndTag
    -0.68
    Personensuche
    -0.63
    <bos>
    -0.63
     Réponses
    -0.60
    rxjs
    -0.59
    Искәрмәләр
    -0.58
    rungsseite
    -0.57
    igshid
    -0.56
    POSITIVE LOGITS
    nezeu
    0.59
     作者
    0.57
    KURZBESCHREIBUNG
    0.57
      (
    0.56
     standby
    0.50
     Authors
    0.50
    structor
    0.49
    Материал
    0.49
    alva
    0.47
    ödie
    0.47
    Activations Density 0.007%

    No Known Activations