© 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. 176
    Prev
    Next
    INDEX
    Explanations

    Numerical data and dates

    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
    Espèce
    -0.60
     parseFrom
    -0.56
     TType
    -0.53
    ">—
    -0.53
     utafitiHapana
    -0.51
    SharedDtor
    -0.49
    RepeatedField
    -0.49
    queryInterface
    -0.48
     Roskov
    -0.47
    Tracce
    -0.46
    POSITIVE LOGITS
    rors
    0.62
     مرئيه
    0.61
     therein
    0.59
    hésite
    0.59
    发表于
    0.57
    ptonshire
    0.57
    ContextHolder
    0.55
    theless
    0.54
    psum
    0.54
    fied
    0.53
    Activations Density 0.005%

    No Known Activations