Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44960
    Prev
    Next
    INDEX
    Explanations

    emails

    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
     messages
    -0.69
     emails
    -0.59
     mails
    -0.57
     slides
    -0.53
    ry
    -0.53
    ting
    -0.49
    Personendaten
    -0.49
    yntaxException
    -0.48
    ly
    -0.47
    ✭✭
    -0.47
    POSITIVE LOGITS
     varmt
    0.62
    athread
    0.62
    holdet
    0.59
    ecutive
    0.58
    hematical
    0.58
     antaranya
    0.57
    orothy
    0.56
    UserScript
    0.56
     chré
    0.56
    úsqueda
    0.55
    Activations Density 0.188%

    No Known Activations