© 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. 4-CLT-HP
    7. 4638
    Prev
    Next
    INDEX
    Explanations

    meet

    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
    -
    -0.56
    ,
    -0.48
     of
    -0.43
     or
    -0.41
    /
    -0.41
     is
    -0.40
     are
    -0.39
     in
    -0.39
    he
    -0.38
    They
    -0.37
    POSITIVE LOGITS
    OGND
    1.12
    IntoConstraints
    1.09
    Portale
    0.99
     كومونز
    0.91
     Efq
    0.88
    хьтан
    0.88
    Jereo
    0.86
     Roskov
    0.86
     展板
    0.84
     GenerationType
    0.84
    Activations Density 0.003%

    No Known Activations