© 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. 3212
    Prev
    Next
    INDEX
    Explanations

    code and state

    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
     зато
    -0.40
    land
    -0.40
    Href
    -0.40
    er
    -0.39
     and
    -0.39
    BLL
    -0.39
    hek
    -0.37
    zub
    -0.37
    ‘
    -0.37
    ']))
    -0.36
    POSITIVE LOGITS
     صوتيه
    0.78
    __(/*!
    0.77
     InputDecoration
    0.76
    IntoConstraints
    0.76
    UnusedPrivate
    0.75
    ServletException
    0.74
     AssemblyCulture
    0.73
    XmlAccessType
    0.73
    onedDateTime
    0.73
     ComVisible
    0.71
    Activations Density 0.001%

    No Known Activations