© 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. 4349
    Prev
    Next
    INDEX
    Explanations

    refugees and displacement

    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
    igli
    -0.54
    unus
    -0.48
    cua
    -0.48
    ecutable
    -0.46
     ut
    -0.44
     못
    -0.44
     pu
    -0.44
     graphing
    -0.44
    hau
    -0.43
    ]='\
    -0.42
    POSITIVE LOGITS
    <bos>
    1.45
     mergeFrom
    0.73
    OGND
    0.68
     autorytatywna
    0.68
     виправивши
    0.67
    Personensuche
    0.65
    Попис
    0.61
     Roskov
    0.60
     Signalez
    0.59
    kloped
    0.57
    Activations Density 0.009%

    No Known Activations