© 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. 0-CLT-HP
    4. 45161
    Prev
    Next
    INDEX
    Explanations

    certainty/subjectivity

    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
    sidemargin
    -0.94
    RetentionPolicy
    -0.92
    IsMutable
    -0.91
    etheless
    -0.90
    daß
    -0.87
     ویکی‌پدیا
    -0.86
    InjectAttribute
    -0.86
     createState
    -0.86
     Савезне
    -0.83
    UserScript
    -0.82
    POSITIVE LOGITS
    .
    0.63
    S
    0.58
    “
    0.55
     Results
    0.54
    st
    0.54
     Question
    0.53
    N
    0.53
     Oil
    0.52
    L
    0.52
    se
    0.51
    Activations Density 0.404%

    No Known Activations