© 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. 0-CLT-HP
    7. 40548
    Prev
    Next
    INDEX
    Explanations

    DVD

    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
    inject
    -0.51
     Den
    -0.49
    ⎣
    -0.49
    ropical
    -0.47
     dé
    -0.47
    ﾞ
    -0.46
    zame
    -0.45
    hape
    -0.44
    mv
    -0.44
    kost
    -0.43
    POSITIVE LOGITS
     Efq
    1.08
     Monfieur
    1.07
     Jefus
    0.93
     Houſe
    0.90
     purpoſe
    0.89
     myſelf
    0.88
     Theſe
    0.85
     houſe
    0.84
    StructEnd
    0.81
     whoſe
    0.80
    Activations Density 0.330%

    No Known Activations