© 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. 338
    Prev
    Next
    INDEX
    Explanations

    fruit

    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
     fruit
    -1.55
     Fruit
    -1.47
    Fruit
    -1.42
    fruit
    -1.25
     FRUIT
    -1.22
     fruits
    -1.20
     Fruits
    -1.16
    fruits
    -1.04
    Fruits
    -0.99
     fruta
    -0.93
    POSITIVE LOGITS
    SequentialGroup
    0.96
     invokingState
    0.84
    GraphicsUnit
    0.80
     صوتيه
    0.74
     utafitiHapana
    0.70
    DeleteBehavior
    0.69
     DBNull
    0.67
    DockStyle
    0.67
     externi
    0.67
    MemoryWarning
    0.66
    Activations Density 0.012%

    No Known Activations