© 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. 5-CLT-HP
    7. 4027
    Prev
    Next
    INDEX
    Explanations

    Dates and times

    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
    Thursday
    -0.68
    Tuesday
    -0.68
     Thursday
    -0.67
    Sunday
    -0.66
    Wednesday
    -0.66
     Sunday
    -0.66
     Wednesday
    -0.66
     Friday
    -0.66
     Tuesday
    -0.65
    Monday
    -0.65
    POSITIVE LOGITS
     drying
    0.61
    metrist
    0.60
     deflate
    0.59
     Shetterly
    0.58
    ifolia
    0.57
    addCriterion
    0.57
     betweenstory
    0.56
     Silurian
    0.54
     Srivastava
    0.54
    ormick
    0.54
    Activations Density 0.047%

    No Known Activations