© 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. 92033
    Prev
    Next
    INDEX
    Explanations

    shielding/protection

    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
     shield
    -0.74
     shielding
    -0.69
     protector
    -0.67
    ifrance
    -0.66
     estimés
    -0.66
    ItemBackground
    -0.66
     protectors
    -0.65
     Teller
    -0.61
    ients
    -0.60
     puissiez
    -0.60
    POSITIVE LOGITS
    brief
    0.47
     tartalomajánló
    0.47
    hept
    0.44
    ater
    0.44
    censo
    0.44
    ere
    0.43
    tle
    0.42
    ->_
    0.42
    Iné
    0.42
    ETRIC
    0.42
    Activations Density 0.072%

    No Known Activations