© 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. 4-CLT-HP
    7. 3483
    Prev
    Next
    INDEX
    Explanations

    positive regard adjectives

    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
     रेटिंग
    -0.61
    highly
    -0.60
     highly
    -0.58
    Highly
    -0.58
    PRNewswire
    -0.52
    tanleria
    -0.51
     gynhyrchwyd
    -0.50
    CUSSION
    -0.50
    각주
    -0.49
     Highly
    -0.49
    POSITIVE LOGITS
    /*
    0.67
    IBarButtonItem
    0.63
    IntoConstraints
    0.60
    AttributeSet
    0.60
    rzost
    0.57
     teachers
    0.56
    maar
    0.55
    preced
    0.54
    awtextra
    0.54
     arche
    0.53
    Activations Density 0.005%

    No Known Activations