© 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. 1-CLT-HP
    7. 45740
    Prev
    Next
    INDEX
    Explanations

    encryption and security

    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
     BoxDecoration
    -0.71
    ंदीखरीदारी
    -0.67
    <bos>
    -0.66
    országban
    -0.56
    Autoritní
    -0.54
     disambiguazione
    -0.53
    География
    -0.53
    GEBURTSDATUM
    -0.53
     lenker
    -0.53
    +#+#
    -0.52
    POSITIVE LOGITS
     Encryption
    0.56
     Crypt
    0.54
     Cipher
    0.53
     cipher
    0.50
     cryptographic
    0.50
     AllMusic
    0.49
     Asser
    0.48
     encryption
    0.48
     crypt
    0.47
    Crypt
    0.46
    Activations Density 0.085%

    No Known Activations