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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3624
    Prev
    Next
    INDEX
    Explanations

    to

    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
    
    -0.80
     resourceCulture
    -0.66
    脚注の使い方
    -0.63
    AccessorTable
    -0.60
    riwal
    -0.60
     }}"></
    -0.59
    ponses
    -0.58
     obstante
    -0.57
     }}"
    -0.57
    GEBURTSDATUM
    -0.56
    POSITIVE LOGITS
     Variability
    0.52
     not
    0.51
    Ethnicity
    0.50
     termica
    0.50
     chaude
    0.49
    ativität
    0.48
     kesk
    0.48
     réglable
    0.48
    hoid
    0.46
     détermin
    0.46
    Activations Density 0.002%

    No Known Activations