© 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. 38754
    Prev
    Next
    INDEX
    Explanations

    entra

    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
     Tek
    -0.64
     entra
    -0.62
     tek
    -0.59
     Kaf
    -0.59
    Tek
    -0.58
    tek
    -0.57
     Roskov
    -0.53
     spons
    -0.50
     LUMP
    -0.50
    ystis
    -0.50
    POSITIVE LOGITS
     eccl
    0.63
    awtextra
    0.59
     оригіналу
    0.56
    EDEFAULT
    0.56
    lin
    0.54
     tegen
    0.54
    횟
    0.52
    XmlAccessType
    0.51
     HasFactory
    0.51
    mbggenerated
    0.50
    Activations Density 0.297%

    No Known Activations