© 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. 5-CLT-HP
    7. 1986
    Prev
    Next
    INDEX
    Explanations

    languages

    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
     &___
    -0.50
     surla
    -0.49
    ReusableCell
    -0.46
    Manbalar
    -0.42
    érité
    -0.42
    ={<
    -0.40
     /><
    -0.40
    setopt
    -0.40
    stretchr
    -0.39
    inerie
    -0.39
    POSITIVE LOGITS
     Ngb
    0.77
    DrawerToggle
    0.69
    IUrlHelper
    0.65
     démo
    0.64
     يتيمه
    0.60
    ruptedException
    0.60
    KommentareTeilen
    0.59
     frequenza
    0.59
    öm
    0.58
     Deel
    0.56
    Activations Density 0.001%

    No Known Activations