© 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. 42047
    Prev
    Next
    INDEX
    Explanations

    |

    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
     |
    -0.91
    .
    -0.91
    |
    -0.86
    ,
    -0.83
    /
    -0.77
    :
    -0.77
    -
    -0.73
     a
    -0.71
     set
    -0.66
     an
    -0.64
    POSITIVE LOGITS
     itſelf
    1.45
     Efq
    1.35
     Theſe
    1.35
     myſelf
    1.30
    +#+#
    1.27
     Houſe
    1.27
     ſeveral
    1.26
    ſelf
    1.25
     дописавши
    1.21
     leaſt
    1.21
    Activations Density 2.316%

    No Known Activations