© 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. 46055
    Prev
    Next
    INDEX
    Explanations

    higher

    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
    hnia
    -0.44
     hore
    -0.43
    gy
    -0.43
    piram
    -0.43
    WithIOException
    -0.42
     độc
    -0.40
     Thur
    -0.40
    lich
    -0.40
     porcentual
    -0.39
    ante
    -0.39
    POSITIVE LOGITS
    Portály
    0.74
     ModelExpression
    0.66
     يتيمه
    0.65
     jurisprudence
    0.64
    endphp
    0.59
     propOrder
    0.59
     enlightenment
    0.57
     जाएगा
    0.57
    LElement
    0.56
     acquaintance
    0.55
    Activations Density 0.118%

    No Known Activations