© 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. 3002
    Prev
    Next
    INDEX
    Explanations

    code/technical writing

    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
    expandindo
    -0.82
    bootstrapcdn
    -0.70
    fromnode
    -0.68
    Aholisi
    -0.67
    IVEREF
    -0.67
    TagMode
    -0.66
    abestanden
    -0.65
    Datuak
    -0.64
    TestingModule
    -0.63
     AssemblyTitle
    -0.62
    POSITIVE LOGITS
    imin
    0.47
    xad
    0.44
    formen
    0.42
     on
    0.41
    ilah
    0.40
    iframe
    0.40
    iserie
    0.39
    InView
    0.39
    former
    0.39
     onPostExecute
    0.39
    Activations Density 0.000%

    No Known Activations