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. 73839
    Prev
    Next
    INDEX
    Explanations

    Technical documentation/code

    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
    culosis
    -0.58
     tapes
    -0.57
     drives
    -0.57
    drives
    -0.54
    tvb
    -0.54
     cassettes
    -0.54
    albums
    -0.54
    amoan
    -0.52
     CRP
    -0.52
     anus
    -0.52
    POSITIVE LOGITS
    thâu
    0.54
    minecraft
    0.54
    /**
    0.52
     BrowserModule
    0.51
    kháu
    0.49
    Билгалдахарш
    0.48
     engraçadas
    0.48
     antaranya
    0.48
    AndGet
    0.47
    LayoutConstraint
    0.47
    Activations Density 0.001%

    No Known Activations