© 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. 0-CLT-HP
    4. 38696
    Prev
    Next
    INDEX
    Explanations

    Scientific/legal evidence and analysis

    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
     evidences
    -0.73
    Evid
    -0.65
    evid
    -0.63
    ibatis
    -0.61
    zyż
    -0.60
     Efq
    -0.60
     Majefty
    -0.59
     Quien
    -0.59
    reszcie
    -0.57
    ſelves
    -0.56
    POSITIVE LOGITS
    Izvori
    0.47
    orap
    0.45
    NameInMap
    0.45
    äumt
    0.45
    awtextra
    0.44
    TYPED
    0.43
    PropTypes
    0.43
    aver
    0.42
    serviceWorker
    0.42
     Wray
    0.42
    Activations Density 0.091%

    No Known Activations