© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97607
    Prev
    Next
    INDEX
    Explanations

    Network Attached Storage (NAS)

    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
     NAS
    -0.54
     hippo
    -0.52
    //
    -0.50
    hippo
    -0.50
    wers
    -0.44
    存于互联网档案馆
    -0.44
    Hippo
    -0.44
    TabPage
    -0.44
    vin
    -0.43
     Kir
    -0.43
    POSITIVE LOGITS
     CreateTagHelper
    0.93
     quæ
    0.79
    RTEE
    0.77
     ivelany
    0.77
     Roskov
    0.75
    berdayakan
    0.74
    úsqueda
    0.73
    ckså
    0.73
     ifrån
    0.69
    ########.
    0.69
    Activations Density 0.175%

    No Known Activations