© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92236
    Prev
    Next
    INDEX
    Explanations

    name

    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
     name
    -0.75
    name
    -0.60
     
    -0.56
     title
    -0.56
     Name
    -0.54
     C
    -0.51
     its
    -0.51
    bin
    -0.49
     H
    -0.49
    mind
    -0.49
    POSITIVE LOGITS
     raiſ
    0.86
     myſelf
    0.85
     Efq
    0.85
     purpoſe
    0.84
     auffi
    0.84
     ſeveral
    0.84
     ainfi
    0.84
     CreateTagHelper
    0.84
     leaſt
    0.83
     Jefus
    0.82
    Activations Density 0.036%

    No Known Activations