© 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. 41233
    Prev
    Next
    INDEX
    Explanations

    alsa

    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
     watermark
    -0.80
     cog
    -0.50
     semblance
    -0.45
     OnInit
    -0.44
    testify
    -0.44
    erdings
    -0.42
    Watermark
    -0.42
     Mann
    -0.42
    ypus
    -0.42
    toria
    -0.41
    POSITIVE LOGITS
    principalTable
    0.77
    LookAnd
    0.73
    ChildScrollView
    0.72
     étoit
    0.70
    :✨
    0.65
     estekak
    0.63
     незавершена
    0.60
     sportiva
    0.59
    Kend
    0.58
    JsonHelper
    0.58
    Activations Density 0.297%

    No Known Activations