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. 0-CLT-HP
    4. 98023
    Prev
    Next
    INDEX
    Explanations

    infection, crime

    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
     ſtate
    -0.77
     AssemblyVersion
    -0.75
     fubject
    -0.75
     Перейти
    -0.74
     ſmall
    -0.73
     })}
    -0.71
     ſeveral
    -0.69
    KURZBESCHREIBUNG
    -0.69
    GEBURTSDATUM
    -0.68
    setViewName
    -0.67
    POSITIVE LOGITS
     and
    0.61
     for
    0.52
    ,
    0.51
    -
    0.47
     Савезне
    0.47
    ValueStyle
    0.46
    WireFormat
    0.41
     acquisition
    0.41
    médi
    0.40
     all
    0.38
    Activations Density 0.015%

    No Known Activations