© 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. 4-CLT-HP
    7. 2919
    Prev
    Next
    INDEX
    Explanations

    period

    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
     AttributeSet
    -0.75
     IFTTT
    -0.75
    <bos>
    -0.74
     Antibiotics
    -0.73
     Constraints
    -0.72
     GIPHY
    -0.72
     Abroad
    -0.71
     Interpol
    -0.71
    ArgsConstructor
    -0.71
     EconPapers
    -0.70
    POSITIVE LOGITS
     or
    0.48
    ,
    0.47
     she
    0.43
     super
    0.42
    ed
    0.42
    /
    0.41
     do
    0.41
     don
    0.40
     too
    0.40
     cho
    0.39
    Activations Density 0.050%

    No Known Activations