© 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. 5-CLT-HP
    7. 95187
    Prev
    Next
    INDEX
    Explanations

    MBA

    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
    efe
    -0.55
    ptos
    -0.49
     Sofia
    -0.49
     Te
    -0.48
    Extension
    -0.47
    ws
    -0.46
     te
    -0.45
    Te
    -0.44
     Capital
    -0.44
    Datuak
    -0.44
    POSITIVE LOGITS
    IndentedString
    0.73
    цездатний
    0.67
    apunov
    0.65
    RefNanny
    0.65
    RegressionTest
    0.60
    ThroughAttribute
    0.60
    enderror
    0.56
    JspWriter
    0.54
    Reactivity
    0.52
     shutterstock
    0.52
    Activations Density 0.001%

    No Known Activations