© 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. 1037
    Prev
    Next
    INDEX
    Explanations

    research studies

    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
    AS
    -0.85
     AS
    -0.85
    ukone
    -0.54
    vale
    -0.52
    ikar
    -0.52
     ITS
    -0.51
    ícia
    -0.51
     ED
    -0.50
     IF
    -0.50
     Shetterly
    -0.50
    POSITIVE LOGITS
    MigrationBuilder
    0.58
    
    0.56
    WireFormat
    0.52
    QFont
    0.52
     spiro
    0.51
    lıyor
    0.51
    Rnd
    0.50
    fjspx
    0.50
     getIntent
    0.49
     tewas
    0.49
    Activations Density 1.105%

    No Known Activations