© 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. 12109
    Prev
    Next
    INDEX
    Explanations

    location

    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
    +#+#
    -0.69
    ship
    -0.67
    note
    -0.63
    thered
    -0.62
     correctes
    -0.60
    ✭✭
    -0.58
    song
    -0.56
    axel
    -0.56
    she
    -0.55
    ]();
    -0.55
    POSITIVE LOGITS
     financières
    0.47
    ingway
    0.45
     financière
    0.43
     argint
    0.43
     وتسجيلات
    0.42
    erdings
    0.42
    textwidth
    0.40
     giai
    0.40
    میزی
    0.40
     spett
    0.40
    Activations Density 0.073%

    No Known Activations