© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2313
    Prev
    Next
    INDEX
    Explanations

    the

    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
     nakalista
    -0.82
     AssemblyCulture
    -0.77
    IntoConstraints
    -0.74
    ReusableCell
    -0.71
     chi̍t
    -0.70
    HomeAsUpEnabled
    -0.68
    XtraEditors
    -0.67
     mergeFrom
    -0.67
    AndEndTag
    -0.64
    hbase
    -0.63
    POSITIVE LOGITS
    ental
    0.48
    yorsunuz
    0.48
     fallu
    0.45
     misses
    0.44
     dropped
    0.40
     thought
    0.40
     assumptions
    0.40
     vyk
    0.39
     need
    0.39
     missed
    0.39
    Activations Density 0.064%

    No Known Activations