© 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. 0-CLT-HP
    7. 97366
    Prev
    Next
    INDEX
    Explanations

    scientific and technical processes

    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
    len
    -0.86
    lin
    -0.78
    llen
    -0.71
     lent
    -0.70
     len
    -0.65
    ThroughAttribute
    -0.63
     lend
    -0.63
    Len
    -0.61
     lends
    -0.61
    lom
    -0.59
    POSITIVE LOGITS
    DllImport
    0.68
    Посилання
    0.58
     Normdatei
    0.57
    UTERS
    0.56
    Життєпис
    0.56
    .*")]
    0.55
    kite
    0.54
     ]
    0.54
    TextWatcher
    0.53
    Дереккөздер
    0.50
    Activations Density 0.688%

    No Known Activations