© 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. 4-CLT-HP
    7. 4419
    Prev
    Next
    INDEX
    Explanations

    /

    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
    出版年
    -0.71
     createState
    -0.64
     cleft
    -0.63
     aapt
    -0.59
    loit
    -0.57
     gorge
    -0.55
    inne
    -0.55
    audiovisuel
    -0.54
    enumi
    -0.52
    ISupport
    -0.52
    POSITIVE LOGITS
    তথ্যসূত্র
    0.49
    #\
    0.45
    IUrlHelper
    0.43
    STS
    0.43
    ósito
    0.43
    DebuggerNonUser
    0.42
    strerror
    0.42
     vérification
    0.41
    >{
    0.40
    sizeCache
    0.40
    Activations Density 0.018%

    No Known Activations