© 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. 0-CLT-HP
    7. 91002
    Prev
    Next
    INDEX
    Explanations

    locations

    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
    located
    -1.24
     located
    -1.10
     situated
    -1.08
     situés
    -0.96
     named
    -0.92
     Located
    -0.90
     situé
    -0.88
     située
    -0.85
     situado
    -0.85
     situada
    -0.83
    POSITIVE LOGITS
    DockStyle
    0.79
    CppMethod
    0.63
    LookAnd
    0.60
    ValueGeneration
    0.57
     esboço
    0.57
    تقاوى
    0.53
    bootstrapcdn
    0.53
    ModelSerializer
    0.51
     Biôgrafia
    0.51
     propOrder
    0.50
    Activations Density 0.102%

    No Known Activations