© 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. 1206
    Prev
    Next
    INDEX
    Explanations

    research

    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
     disambiguazione
    -1.02
    MigrationBuilder
    -0.97
    DockStyle
    -0.96
    KURZBESCHREIBUNG
    -0.91
     cherchés
    -0.90
     تضيفلها
    -0.87
    LookAnd
    -0.84
     виправивши
    -0.83
    tvguidetime
    -0.80
    ंदीखरीदारी
    -0.79
    POSITIVE LOGITS
     you
    0.59
    :
    0.44
    you
    0.44
     (
    0.44
     YOU
    0.40
     but
    0.38
     You
    0.38
    You
    0.37
     вам
    0.36
     
    0.36
    Activations Density 0.007%

    No Known Activations