© 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. 4-CLT-HP
    7. 1768
    Prev
    Next
    INDEX
    Explanations

    very

    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
    Rüyada
    -0.73
     Theſe
    -0.68
    NewUrlParser
    -0.65
     Monfieur
    -0.65
     myſelf
    -0.65
     ―――――
    -0.60
     Eſ
    -0.60
     Efq
    -0.59
     iſt
    -0.59
    رشف
    -0.59
    POSITIVE LOGITS
     Pop
    0.59
     Stre
    0.56
     Pen
    0.54
    setCellValue
    0.53
     Sim
    0.50
     Str
    0.49
     Per
    0.48
     Pick
    0.48
     mission
    0.47
     pop
    0.47
    Activations Density 0.005%

    No Known Activations