© 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. 2079
    Prev
    Next
    INDEX
    Explanations

    Code/technical snippets

    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
     giro
    -0.53
     الميل
    -0.52
     a
    -0.51
    APIView
    -0.48
    asteroide
    -0.48
     career
    -0.47
    pushd
    -0.47
    AuthToken
    -0.46
    audiovisuel
    -0.46
     rings
    -0.46
    POSITIVE LOGITS
    
    0.88
    AndEndTag
    0.63
    \{\\
    0.63
    setVerticalGroup
    0.62
    VIAF
    0.60
    MemoryWarning
    0.59
    ProcessEvent
    0.57
    everyone
    0.56
    ::::::::
    0.52
     apporté
    0.52
    Activations Density 0.003%

    No Known Activations