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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73974
    Prev
    Next
    INDEX
    Explanations

    elin

    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
    Trust
    -0.50
     plancher
    -0.50
    }))
    
    -0.49
     TType
    -0.49
    issipp
    -0.49
    trust
    -0.48
    alga
    -0.48
    Cyfeiriadau
    -0.48
     }))
    -0.48
    oflu
    -0.47
    POSITIVE LOGITS
    ScopeManager
    0.61
    脚注の使い方
    0.59
    RenderAtEndOf
    0.56
     AssemblyProduct
    0.55
    InitVars
    0.51
    Ārējās
    0.50
    #+#
    0.48
    verifyException
    0.48
     surla
    0.47
     يتيمه
    0.45
    Activations Density 0.001%

    No Known Activations