© 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. 1-CLT-HP
    7. 45761
    Prev
    Next
    INDEX
    Explanations

    towers or pivotal

    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
     tower
    -0.73
    ControllerTest
    -0.66
    WebVitals
    -0.65
    Personendaten
    -0.63
    tower
    -0.63
     transfieras
    -0.60
    GraphicsUnit
    -0.59
     nakalista
    -0.58
    Tower
    -0.57
     Tower
    -0.56
    POSITIVE LOGITS
    Pick
    0.50
    oodoo
    0.50
     pick
    0.50
     Pick
    0.48
    recated
    0.48
    pick
    0.48
    Hintergrund
    0.47
     pageContext
    0.46
     null
    0.45
    kapp
    0.45
    Activations Density 0.111%

    No Known Activations