© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2214
    Prev
    Next
    INDEX
    Explanations

    investigative

    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
     MERCHANTABILITY
    -0.53
     ketidak
    -0.49
     unlikely
    -0.49
     danni
    -0.48
     Semoga
    -0.48
    PINES
    -0.48
     Gulch
    -0.48
    chengladbach
    -0.47
    mers
    -0.47
    Зноскі
    -0.47
    POSITIVE LOGITS
     transférez
    0.67
     AssemblyCulture
    0.64
    tonsoft
    0.63
    +#+#
    0.59
     PhpStorm
    0.54
    oredCriteria
    0.54
    Rohy
    0.53
    DoubleQuotes
    0.50
     Jop
    0.50
     myſelf
    0.50
    Activations Density 0.001%

    No Known Activations