© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42080
    Prev
    Next
    INDEX
    Explanations

    command, CPU

    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
     loose
    -0.89
     command
    -0.79
    loose
    -0.76
     Command
    -0.69
    Loose
    -0.68
     looser
    -0.66
    command
    -0.65
    Command
    -0.62
     loosely
    -0.58
     Loose
    -0.57
    POSITIVE LOGITS
    OGND
    0.84
    expandindo
    0.82
    istoitu
    0.75
     springfox
    0.74
    kloped
    0.73
    RectangleBorder
    0.72
    setof
    0.71
     jdbcTemplate
    0.70
    forChild
    0.69
    gameserver
    0.69
    Activations Density 0.173%

    No Known Activations