© 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. 0-CLT-HP
    7. 93390
    Prev
    Next
    INDEX
    Explanations

    blues music

    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
    észetes
    -0.67
    MessageTagHelper
    -0.65
     blues
    -0.61
     تضيفلها
    -0.59
     Were
    -0.57
    Билгалдахарш
    -0.57
     sost
    -0.55
    Were
    -0.53
     remb
    -0.52
    backtracking
    -0.52
    POSITIVE LOGITS
    antMatchers
    0.49
    twimg
    0.46
    PickerController
    0.44
    uxxxx
    0.43
    appropriate
    0.41
    ness
    0.41
    cule
    0.41
     tục
    0.40
    '][]
    0.40
     StringTokenizer
    0.40
    Activations Density 0.043%

    No Known Activations