© 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. 45523
    Prev
    Next
    INDEX
    Explanations

    text snippets

    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
     who
    -0.51
    who
    -0.47
     whose
    -0.46
     okhttp
    -0.46
     pinulongan
    -0.46
     innere
    -0.44
     which
    -0.43
     sqlSession
    -0.43
    .
    -0.43
    ูป
    -0.42
    POSITIVE LOGITS
     linkovi
    0.86
    Véxase
    0.79
    AddTagHelper
    0.75
    RTDA
    0.66
    bootstrapcdn
    0.66
     propOrder
    0.65
     is
    0.65
     Administrativna
    0.65
    Amicalement
    0.65
    ########.
    0.64
    Activations Density 0.623%

    No Known Activations