© 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. 95165
    Prev
    Next
    INDEX
    Explanations

    academic/medical research

    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
     }}"></
    -0.51
    
    -0.49
     Protección
    -0.48
    FormTagHelper
    -0.44
     justify
    -0.44
     numerus
    -0.43
     subtlety
    -0.43
    atan
    -0.43
    FormState
    -0.43
     portability
    -0.42
    POSITIVE LOGITS
    PhysRevD
    0.89
     betweenstory
    0.68
    IsContent
    0.63
    principalTable
    0.63
    Portale
    0.58
     الرياضيه
    0.57
     gué
    0.56
     condamné
    0.55
    __(/*!
    0.54
    ARROLL
    0.53
    Activations Density 0.001%

    No Known Activations