© 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. 95074
    Prev
    Next
    INDEX
    Explanations

    Nic

    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
     facie
    -0.52
    isDebugEnabled
    -0.52
     AppBundle
    -0.52
     Tula
    -0.50
    neux
    -0.48
     REA
    -0.47
     THEOD
    -0.47
     unit
    -0.46
     Esq
    -0.46
     Heer
    -0.46
    POSITIVE LOGITS
    Personensuche
    0.81
    otine
    0.77
    ValueStyle
    0.73
     betweenstory
    0.59
    ContentAsync
    0.57
    Filmographie
    0.57
     незавершена
    0.54
     يتيمه
    0.54
    transQ
    0.54
    Personendaten
    0.52
    Activations Density 0.001%

    No Known Activations