© 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. 1094
    Prev
    Next
    INDEX
    Explanations

    oversized

    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
    -0.82
    OGND
    -0.71
    verwijspagina
    -0.65
    stdc
    -0.64
     OFDb
    -0.62
    Anhalt
    -0.60
     pinulongan
    -0.60
     thee
    -0.59
     AssemblyTitle
    -0.58
     initComponents
    -0.58
    POSITIVE LOGITS
    zdo
    0.50
    clero
    0.48
     cere
    0.47
     Leisure
    0.45
     Cher
    0.45
    pyrid
    0.44
     glabrous
    0.42
     Doppler
    0.42
    Abit
    0.42
    QUES
    0.41
    Activations Density 0.092%

    No Known Activations