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. 20-CLT-HP
    4. 73901
    Prev
    Next
    INDEX
    Explanations

    /

    np_max-act-logits · 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
     виправивши
    -0.69
    %)$
    -0.60
    PYX
    -0.52
    Personendaten
    -0.52
     كومونز
    -0.52
    pinephrine
    -0.51
    Zacks
    -0.50
     Gaylord
    -0.50
     GSP
    -0.50
     Bridgeport
    -0.49
    POSITIVE LOGITS
    ReusableCell
    0.58
    OpenHelper
    0.56
    jsdelivr
    0.54
    Whilst
    0.52
    IconModule
    0.52
     preocupes
    0.49
    MotionEvent
    0.49
     dė
    0.48
    HostException
    0.48
    wörter
    0.47
    Activations Density 0.001%

    No Known Activations