© 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. 20-CLT-HP
    7. 75020
    Prev
    Next
    INDEX
    Explanations

    code with colons

    np_max-act-logits · 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
    veri
    -0.47
     Masking
    -0.38
    στη
    -0.38
    IsMutable
    -0.38
     fis
    -0.38
     Thi
    -0.37
     Nadel
    -0.36
     fiscal
    -0.36
     thay
    -0.36
     accepted
    -0.35
    POSITIVE LOGITS
    CppMethod
    0.86
    SharedDtor
    0.84
    LookAnd
    0.77
    +#+#
    0.77
    aarrggbb
    0.74
    verwijspagina
    0.72
     Efq
    0.72
    oa̍t
    0.70
    MLLoader
    0.69
    ########.
    0.68
    Activations Density 0.013%

    No Known Activations