Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45032
    Prev
    Next
    INDEX
    Explanations

    loosen

    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
     betweenstory
    -1.30
    RenderAtEndOf
    -1.29
    aarrggbb
    -1.15
    RetentionPolicy
    -1.11
    Personendaten
    -1.07
     weaken
    -1.06
     disambiguazione
    -1.06
    WithIOException
    -1.03
     weakens
    -1.02
     AssemblyCompany
    -0.98
    POSITIVE LOGITS
     up
    0.97
     in
    0.65
     to
    0.60
     "
    0.60
     the
    0.60
    ley
    0.59
     full
    0.59
    up
    0.57
     U
    0.57
     '
    0.56
    Activations Density 1.585%

    No Known Activations