© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41506
    Prev
    Next
    INDEX
    Explanations

    Problems, difficulties

    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
     shadow
    -0.68
     trouble
    -0.62
    shadow
    -0.60
     Shadow
    -0.55
     nest
    -0.55
     large
    -0.51
     strong
    -0.50
     long
    -0.49
     Snow
    -0.49
     for
    -0.48
    POSITIVE LOGITS
    +#+#
    1.15
    Personendaten
    1.00
     Exacts
    0.99
    ValueStyle
    0.98
     Jefus
    0.93
     Reſ
    0.91
     Houſe
    0.90
    StructEnd
    0.90
    SourceChecksum
    0.90
     houſe
    0.89
    Activations Density 0.323%

    No Known Activations