© 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. 91140
    Prev
    Next
    INDEX
    Explanations

    open

    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
     open
    -0.94
    open
    -0.73
     Open
    -0.72
    Open
    -0.65
     OPEN
    -0.65
     offenen
    -0.64
    lossenen
    -0.63
    开放
    -0.59
    esModule
    -0.58
    entant
    -0.57
    POSITIVE LOGITS
     löytyy
    0.49
    ApiProperty
    0.48
     vermelhas
    0.47
    Lynx
    0.47
    uresti
    0.47
     Jdbc
    0.46
     œufs
    0.46
    yafet
    0.46
    ckså
    0.45
     up
    0.45
    Activations Density 0.030%

    No Known Activations