© 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. 3110
    Prev
    Next
    INDEX
    Explanations

    falling/negative events

    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
    <bos>
    -0.69
    +#+#
    -0.66
     Vikipedi
    -0.64
    Personendaten
    -0.64
     unknownFields
    -0.62
    الإنجليزية
    -0.57
    QMetaType
    -0.57
    SourceChecksum
    -0.57
    gameserver
    -0.56
     ModelExpression
    -0.55
    POSITIVE LOGITS
     odkazy
    0.60
     upon
    0.59
     CURIAM
    0.54
    $}}
    0.51
    korb
    0.51
     down
    0.51
     Dropdown
    0.50
    cursed
    0.50
    dropdown
    0.49
    OMB
    0.48
    Activations Density 0.003%

    No Known Activations