© 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. 4-CLT-HP
    7. 4325
    Prev
    Next
    INDEX
    Explanations

    Negative or problematic situations

    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
    تام
    -0.50
     numerus
    -0.47
    SourceChecksum
    -0.47
    ред
    -0.45
     rä
    -0.41
    yelitis
    -0.41
    oriasis
    -0.41
    ποτε
    -0.40
    UGHT
    -0.40
    GetInstance
    -0.40
    POSITIVE LOGITS
     néz
    0.66
     vehicles
    0.65
     to
    0.62
     fallu
    0.62
     remplacé
    0.62
    vehicles
    0.60
     juger
    0.60
     refusé
    0.57
    TestingModule
    0.57
     tools
    0.56
    Activations Density 0.001%

    No Known Activations