Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12479
    Prev
    Next
    INDEX
    Explanations

    Israel-Palestine conflict

    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
     itſelf
    -0.84
     dezelve
    -0.75
     zoude
    -0.74
    reszcie
    -0.71
     picioare
    -0.71
     möge
    -0.69
     zijne
    -0.69
    geführt
    -0.68
     zelve
    -0.68
     يتيمه
    -0.68
    POSITIVE LOGITS
    ServiceModel
    0.52
    secre
    0.51
     dat
    0.50
     ho
    0.49
     che
    0.46
    toContain
    0.46
     ran
    0.45
     String
    0.44
     adel
    0.44
     cor
    0.44
    Activations Density 0.022%

    No Known Activations