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. 20-CLT-HP
    4. 74444
    Prev
    Next
    INDEX
    Explanations

    time

    np_max-act-logits · 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
     Sixteenth
    -0.49
    PRESA
    -0.48
    JScrollPane
    -0.46
     stück
    -0.44
    tización
    -0.42
     Cæsar
    -0.42
    ChromeDriver
    -0.42
    icanos
    -0.42
    PropertyChanged
    -0.41
    figsize
    -0.40
    POSITIVE LOGITS
     domain
    0.63
     disponibilités
    0.61
    domain
    0.60
    Personendaten
    0.60
     inter
    0.58
     Accesat
    0.58
    ViewFeatures
    0.57
    󠁢
    0.57
     الحره
    0.57
     defStyle
    0.56
    Activations Density 0.001%

    No Known Activations