© 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. 90682
    Prev
    Next
    INDEX
    Explanations

    diesel

    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
    DockStyle
    -0.90
     >=",
    -0.58
     PropertyChanged
    -0.51
    AndEndTag
    -0.48
     iconLine
    -0.45
    endency
    -0.45
    WriteAttribute
    -0.44
    Referències
    -0.42
    ngdoc
    -0.42
     tillgäng
    -0.42
    POSITIVE LOGITS
    ized
    0.76
    ly
    0.66
    ised
    0.66
    isms
    0.62
    iously
    0.60
    ific
    0.59
    ities
    0.59
    ism
    0.59
    Hentet
    0.58
    ement
    0.57
    Activations Density 0.309%

    No Known Activations