© 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. 1-CLT-HP
    4. 801
    Prev
    Next
    INDEX
    Explanations

    guess

    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
    Guess
    -0.86
     Guess
    -0.81
    Anyway
    -0.75
     guess
    -0.71
     Anyway
    -0.67
    anyway
    -0.64
    MLLoader
    -0.63
     myſelf
    -0.61
     scolaire
    -0.61
    guess
    -0.59
    POSITIVE LOGITS
    ie
    0.60
     you
    0.56
    culable
    0.51
     jScrollPane
    0.50
    sie
    0.49
     it
    0.48
     Normdatei
    0.48
    gie
    0.47
    yy
    0.47
     they
    0.47
    Activations Density 0.008%

    No Known Activations