© 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. 2060
    Prev
    Next
    INDEX
    Explanations

    signal

    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
     Signals
    -0.69
     signals
    -0.67
     signal
    -0.66
    signal
    -0.66
    GeneratedCode
    -0.66
    Signal
    -0.64
     Signal
    -0.62
     مرئيه
    -0.56
     vettoriale
    -0.55
    -------------</
    -0.55
    POSITIVE LOGITS
    дента
    0.62
    TacToe
    0.52
     @"/
    0.52
    bcryptjs
    0.52
    ousness
    0.52
     it
    0.49
    ForKey
    0.49
    Erfolge
    0.48
    ydd
    0.48
     defStyle
    0.47
    Activations Density 0.195%

    No Known Activations