© 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. 90739
    Prev
    Next
    INDEX
    Explanations

    inspector

    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
     IV
    -0.64
    veling
    -0.59
     van
    -0.58
    cep
    -0.53
    icolo
    -0.47
    ids
    -0.45
    <eos>
    -0.45
    anmoins
    -0.45
    veled
    -0.44
    летний
    -0.44
    POSITIVE LOGITS
     Efq
    1.20
     Majefty
    1.17
     myſelf
    1.14
    +#+#
    1.09
     Houſe
    1.09
     itſelf
    1.08
     pleaſure
    1.05
     Monfieur
    1.05
     Diſ
    1.04
     Eſ
    1.04
    Activations Density 0.068%

    No Known Activations