© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11847
    Prev
    Next
    INDEX
    Explanations

    talking about conditions

    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
     فريبيس
    -0.73
    WithIOException
    -0.65
    ExecuteReader
    -0.57
    windowFixed
    -0.55
    DockStyle
    -0.53
     viewDidLoad
    -0.53
    makeText
    -0.52
     WaitForSeconds
    -0.51
    Чыганаклар
    -0.50
     PublicKey
    -0.49
    POSITIVE LOGITS
    zheimer
    0.56
    cknow
    0.53
    гда
    0.52
     cannibal
    0.52
    hlander
    0.51
    ativity
    0.51
     Untitled
    0.51
    gether
    0.50
     untitled
    0.50
     Lando
    0.50
    Activations Density 0.023%

    No Known Activations