© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92932
    Prev
    Next
    INDEX
    Explanations

    wedge

    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
    a
    -0.94
     Diſ
    -0.93
     Anſ
    -0.88
    tır
    -0.85
     Reſ
    -0.85
    s
    -0.84
     Theſe
    -0.83
     Beſ
    -0.81
     Majefty
    -0.81
     raiſ
    -0.80
    POSITIVE LOGITS
    ">\
    0.52
    ness
    0.50
     P
    0.49
    "]:
    0.49
     pageContext
    0.48
     O
    0.48
     ro
    0.48
    ning
    0.48
    ']:
    0.47
     فريبيس
    0.47
    Activations Density 0.067%

    No Known Activations