© 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. 1-CLT-HP
    7. 12120
    Prev
    Next
    INDEX
    Explanations

    process

    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
    RegistryLite
    -0.71
    DockStyle
    -0.64
     ویکی‌پدیا
    -0.56
     kasarigan
    -0.55
    يكب
    -0.54
    oa̍t
    -0.53
    TagMode
    -0.52
     sockaddr
    -0.52
    GoogleApiClient
    -0.51
     AttributeSet
    -0.51
    POSITIVE LOGITS
    ations
    0.65
     chain
    0.57
    ability
    0.57
     متعلقه
    0.55
    ation
    0.55
     canst
    0.53
    ορ
    0.53
     Vea
    0.52
    ableness
    0.52
    alse
    0.51
    Activations Density 0.012%

    No Known Activations