© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91410
    Prev
    Next
    INDEX
    Explanations

    Mixed contexts: code, news

    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
     itſelf
    -0.82
     himſelf
    -0.68
    FieldBuilder
    -0.65
     themſelves
    -0.63
     myſelf
    -0.61
    ViewImports
    -0.60
     purpoſe
    -0.59
     uſ
    -0.57
    __':
    -0.56
    ſelves
    -0.56
    POSITIVE LOGITS
     this
    0.64
     because
    0.61
     to
    0.57
     given
    0.56
     by
    0.54
     due
    0.53
     क्योंकि
    0.52
     vanwege
    0.52
     as
    0.51
     of
    0.51
    Activations Density 0.000%

    No Known Activations