© 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. 2000
    Prev
    Next
    INDEX
    Explanations

    research reports and effects

    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
    Personendaten
    -0.80
    NameInMap
    -0.74
     дописавши
    -0.66
    \{\\
    -0.64
     propOrder
    -0.64
    ModelAdmin
    -0.61
    UnusedPrivate
    -0.61
     gyhoeddwyd
    -0.61
     الرياضيه
    -0.60
    IsMutable
    -0.60
    POSITIVE LOGITS
    EndInit
    0.52
    StartTag
    0.51
    Życiorys
    0.50
     negativos
    0.49
    stddef
    0.49
    Pla
    0.49
    Placa
    0.47
     Porém
    0.47
     JTextArea
    0.46
    MediaStore
    0.46
    Activations Density 0.001%

    No Known Activations