© 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. 5-CLT-HP
    7. 3112
    Prev
    Next
    INDEX
    Explanations

    in

    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
    CloseOperation
    -0.90
    OGND
    -0.87
    SequentialGroup
    -0.82
    awtextra
    -0.75
    FieldBuilder
    -0.75
     ainfi
    -0.72
    InputBorder
    -0.72
    AndEndTag
    -0.71
     noDo
    -0.70
    ंदीखरीदारी
    -0.69
    POSITIVE LOGITS
    -
    0.43
     mechanical
    0.36
    SerializedName
    0.36
    醐
    0.36
     computer
    0.34
     STEM
    0.33
     fore
    0.33
     szen
    0.33
     prů
    0.33
     lieber
    0.33
    Activations Density 0.002%

    No Known Activations