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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44596
    Prev
    Next
    INDEX
    Explanations

    host

    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
     host
    -2.47
     Host
    -2.34
    Host
    -2.25
    host
    -2.17
     HOST
    -2.05
     hosting
    -1.95
    HOST
    -1.93
     hosts
    -1.83
     hosted
    -1.77
     Hosts
    -1.70
    POSITIVE LOGITS
     NSCoder
    0.67
     themſelves
    0.65
     myſelf
    0.64
     Shakspeare
    0.62
     negroes
    0.59
     himſelf
    0.56
    inctive
    0.56
     Negroes
    0.55
     perfons
    0.54
    lihood
    0.54
    Activations Density 0.047%

    No Known Activations