© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45723
    Prev
    Next
    INDEX
    Explanations

    Stating an opinion or argument

    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
     target
    -0.53
     rem
    -0.52
    codable
    -0.50
     foot
    -0.50
    quelize
    -0.49
    rometer
    -0.49
    ajoz
    -0.48
     arm
    -0.48
     tongue
    -0.48
     ch
    -0.48
    POSITIVE LOGITS
    tagHelperRunner
    1.20
     متعلقه
    0.79
    rungsseite
    0.79
    ########.
    0.68
     autorytatywna
    0.67
     ErrInvalid
    0.66
    harusnya
    0.66
    ViewImports
    0.65
    Бахар
    0.65
    thenReturn
    0.64
    Activations Density 0.158%

    No Known Activations