© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 2916
    Prev
    Next
    INDEX
    Explanations

    probably

    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
     to
    -0.59
     of
    -0.54
    خي
    -0.53
     quite
    -0.52
    خی
    -0.51
    bacher
    -0.50
    Aktualisiert
    -0.49
     less
    -0.47
     ')[
    -0.46
    ียด
    -0.46
    POSITIVE LOGITS
     would
    1.16
     wouldn
    1.15
     will
    1.15
     isn
    1.11
     wasn
    1.02
     doesn
    0.97
    would
    0.93
     hasn
    0.92
     does
    0.91
     didn
    0.91
    Activations Density 0.005%

    No Known Activations