© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5599
    Prev
    Next
    INDEX
    Explanations

    Code and file paths

    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
    +"/"+
    -0.57
    例文帳に追加
    -0.56
    +"/
    -0.54
     redor
    -0.54
    >),
    -0.54
    elif
    -0.53
    ]=="
    -0.53
    ')
    -0.52
     or
    -0.52
    else
    -0.52
    POSITIVE LOGITS
     SafeMath
    0.71
    PreferredItem
    0.65
     TimeUnit
    0.65
     الرياضيه
    0.65
    uisine
    0.63
     NDEBUG
    0.60
    abestanden
    0.59
    enfance
    0.59
    CloseOperation
    0.58
     sumpay
    0.58
    Activations Density 0.001%

    No Known Activations