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. 1-CLT-HP
    4. 45291
    Prev
    Next
    INDEX
    Explanations

    version

    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
     inspiradoras
    -0.52
    はじめに
    -0.51
    TestingModule
    -0.49
    lazione
    -0.48
    gridx
    -0.47
     pinulongan
    -0.47
    ineno
    -0.46
     personnelles
    -0.45
    readable
    -0.45
    éndolo
    -0.45
    POSITIVE LOGITS
     BoxDecoration
    0.58
     Spisak
    0.57
    ">:
    0.55
     onCancelled
    0.55
    AutoScaleMode
    0.54
    kmäler
    0.54
     mif
    0.54
     canes
    0.53
     xanth
    0.51
    "])
    
    0.51
    Activations Density 0.003%

    No Known Activations