Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74362
    Prev
    Next
    INDEX
    Explanations

    Technical/formal writing

    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
    EndContext
    -0.67
     CreateTagHelper
    -0.59
     htons
    -0.57
     الرياضيه
    -0.57
     Chwiliwch
    -0.55
    thouses
    -0.53
     disambiguazione
    -0.52
    PyExc
    -0.52
    rophes
    -0.51
     ExecuteAsync
    -0.51
    POSITIVE LOGITS
    CPtr
    0.49
    CodeAttribute
    0.47
    %=
    0.45
     مشين
    0.45
    }))
    
    0.42
    مصادر
    0.42
     onBind
    0.40
    })).
    0.39
    (≧
    0.39
    Vidite
    0.39
    Activations Density 0.001%

    No Known Activations