© 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. 5-CLT-HP
    7. 2233
    Prev
    Next
    INDEX
    Explanations

    valley

    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
     Urugu
    -0.54
    ="#"><
    -0.50
    Capítulo
    -0.47
     verrez
    -0.47
     éto
    -0.46
    itle
    -0.45
     désactiv
    -0.45
    hien
    -0.45
    Bung
    -0.45
     уч
    -0.44
    POSITIVE LOGITS
    OGND
    0.70
     disambiguazione
    0.60
     noDo
    0.60
     AssemblyVersion
    0.60
    verwijspagina
    0.59
    TypedDataSet
    0.59
    aarrggbb
    0.59
    يكب
    0.57
    (!__
    0.55
    出版年
    0.54
    Activations Density 0.000%

    No Known Activations