© 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. 94954
    Prev
    Next
    INDEX
    Explanations

    predictions

    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
    saraba
    -1.22
    GEBURTSDATUM
    -1.17
    RectangleBorder
    -1.13
    ReusableCell
    -1.10
     beginnetje
    -1.10
     '\\;'
    -1.09
    DockStyle
    -1.08
     ujednoznacz
    -1.08
    likely
    -1.07
     تضيفلها
    -1.07
    POSITIVE LOGITS
    ↵
    0.50
    in
    0.49
    vi
    0.48
    ↵↵
    0.46
    P
    0.45
    hi
    0.44
    —
    0.44
    –
    0.44
    at
    0.43
     P
    0.43
    Activations Density 0.015%

    No Known Activations