© 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. 2042
    Prev
    Next
    INDEX
    Explanations

    seeking help/understanding

    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
     незавершена
    -0.66
     unknown
    -0.54
     nor
    -0.52
     дописавши
    -0.51
     hadn
    -0.48
    กำลัง
    -0.48
    RC
    -0.47
     Privacidade
    -0.47
     Nor
    -0.47
    many
    -0.47
    POSITIVE LOGITS
     nahilalakip
    0.65
     AssemblyProduct
    0.56
     препратки
    0.55
    xtext
    0.54
     Signalez
    0.51
    artifactId
    0.51
     createSlice
    0.50
     Infórmanos
    0.50
    verwijspagina
    0.49
    vri
    0.49
    Activations Density 0.090%

    No Known Activations