© 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. 1935
    Prev
    Next
    INDEX
    Explanations

    journalism

    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
     ModelExpression
    -1.06
    GEBURTSDATUM
    -0.93
     autorytatywna
    -0.87
     виправивши
    -0.83
    Hentet
    -0.82
     betweenstory
    -0.77
    بوابة
    -0.74
    ंदीखरीदारी
    -0.74
     كومونز
    -0.74
    #+#
    -0.74
    POSITIVE LOGITS
     juridiques
    0.44
    инг
    0.44
     boş
    0.43
     religieuses
    0.43
     plass
    0.43
    posti
    0.43
     Wetter
    0.42
     ovvero
    0.41
    Italie
    0.40
     abstrait
    0.40
    Activations Density 1.716%

    No Known Activations