© 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. 1-CLT-HP
    7. 11799
    Prev
    Next
    INDEX
    Explanations

    Tales

    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
    Datuak
    -0.85
    localctx
    -0.78
    Zeneca
    -0.76
     AppCompatTheme
    -0.76
    Autoritní
    -0.74
     &___
    -0.74
    naeus
    -0.70
    OptionsMenu
    -0.69
    okovic
    -0.69
    TagMode
    -0.69
    POSITIVE LOGITS
    ImageContext
    0.55
    onAttach
    0.49
     Auto
    0.44
    s
    0.41
    ∩
    0.40
     PropTypes
    0.38
     from
    0.37
     presentado
    0.36
    multer
    0.36
     pasar
    0.36
    Activations Density 0.128%

    No Known Activations