© 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. 1-CLT-HP
    7. 10763
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
     Tinker
    -1.85
     tinker
    -0.95
     quæ
    -0.86
     myſelf
    -0.75
     uſed
    -0.71
     leaſt
    -0.69
     themſelves
    -0.68
     purpoſe
    -0.67
     uſe
    -0.66
     Efq
    -0.66
    POSITIVE LOGITS
    bell
    0.63
     برانيه
    0.58
    bells
    0.53
    OrNil
    0.53
     Bells
    0.53
     pulumi
    0.53
    enumi
    0.51
    er
    0.50
    ER
    0.49
    LookAnd
    0.48
    Activations Density 0.007%

    No Known Activations