© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71608
    Prev
    Next
    INDEX
    Explanations

    self

    np_max-act-logits · 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
    StoryboardSegue
    -0.80
    AndEndTag
    -0.70
     CreateTagHelper
    -0.66
    sizeCache
    -0.65
    RegressionTest
    -0.63
     autorytatywna
    -0.63
    #
    -0.58
     îna
    -0.55
     gomma
    -0.54
    RenderAtEndOf
    -0.51
    POSITIVE LOGITS
     self
    2.89
     Self
    2.33
    self
    2.25
    Self
    2.16
     SELF
    2.08
    SELF
    1.69
     Selbst
    1.47
     selves
    1.45
     sel
    1.34
    Selbst
    1.27
    Activations Density 0.001%

    No Known Activations