© 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. 326
    Prev
    Next
    INDEX
    Explanations

    hard drives/magnetic storage

    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
     magnetic
    -0.67
    <bos>
    -0.56
    磁
    -0.55
     Magnetic
    -0.54
    magnetic
    -0.52
     магнит
    -0.50
    '
    -0.50
     magne
    -0.47
    ise
    -0.47
    Magnetic
    -0.47
    POSITIVE LOGITS
     ſtate
    0.82
     purpoſe
    0.80
     becauſe
    0.78
    MethodManager
    0.77
     houſe
    0.76
     preſent
    0.74
    ſelf
    0.73
     raiſ
    0.73
     useAppContext
    0.71
     chond
    0.70
    Activations Density 0.039%

    No Known Activations