© 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. 96688
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    __":
    -0.69
    MLLoader
    -0.66
    __':
    -0.62
     <<<<<<<<<<<<<<
    -0.61
    interopRequire
    -0.60
    __':
    -0.60
    endpush
    -0.59
    __":
    -0.58
    ParallelGroup
    -0.58
    LabelTagHelper
    -0.57
    POSITIVE LOGITS
     particuliers
    0.61
    alnız
    0.60
     čierna
    0.57
     entstanden
    0.56
     suivantes
    0.55
    ichtliche
    0.54
    oksi
    0.54
    })));
    0.53
     traités
    0.53
     immédi
    0.52
    Activations Density 0.001%

    No Known Activations