© 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. 45303
    Prev
    Next
    INDEX
    Explanations

    select

    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
     select
    -2.34
    select
    -2.09
     selected
    -1.92
    Select
    -1.87
     selects
    -1.84
     Select
    -1.82
    selected
    -1.72
     Selected
    -1.66
    Selected
    -1.65
     choose
    -1.64
    POSITIVE LOGITS
     to
    0.82
     a
    0.62
     Numerade
    0.62
     another
    0.59
     ProtoMessage
    0.58
     for
    0.57
     the
    0.57
     TextAppearance
    0.56
     door
    0.55
    asci
    0.55
    Activations Density 0.059%

    No Known Activations