© 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. 0-CLT-HP
    7. 44170
    Prev
    Next
    INDEX
    Explanations

    Software

    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
    software
    -0.93
    Software
    -0.78
     referenties
    -0.78
     software
    -0.75
     SOFTWARE
    -0.75
    principalTable
    -0.75
     Software
    -0.73
     Aerospace
    -0.69
     Pharmaceutical
    -0.68
     Roskov
    -0.68
    POSITIVE LOGITS
     <=",
    0.51
    ValueStyle
    0.47
     backing
    0.41
     revanche
    0.40
     iprot
    0.38
     attention
    0.38
     need
    0.37
     preparation
    0.37
     demand
    0.37
     failure
    0.36
    Activations Density 0.733%

    No Known Activations