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. 12569
    Prev
    Next
    INDEX
    Explanations

    community

    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
    ennifer
    -0.68
    soever
    -0.66
     itſelf
    -0.65
    hassee
    -0.64
     holotype
    -0.63
     estekak
    -0.63
    ChildScrollView
    -0.63
     StringTokenizer
    -0.63
     distillery
    -0.61
     Wikisource
    -0.60
    POSITIVE LOGITS
     Hot
    0.47
    ms
    0.46
    áticos
    0.45
     on
    0.44
    #+#
    0.44
     New
    0.44
     cut
    0.43
    MemoryWarning
    0.43
     hurt
    0.42
     Israel
    0.41
    Activations Density 0.048%

    No Known Activations