© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2530
    Prev
    Next
    INDEX
    Explanations

    guiding through a 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
     tartalomajánló
    -0.93
     EconPapers
    -0.89
     kasarigan
    -0.81
    évaluateur
    -0.81
    NOPQRST
    -0.78
    पया
    -0.71
    ibatis
    -0.70
    SharedDtor
    -0.69
    gameserver
    -0.67
    XmlAccessorType
    -0.66
    POSITIVE LOGITS
     the
    0.91
     each
    0.67
     all
    0.66
     steps
    0.60
     every
    0.59
     finding
    0.59
     how
    0.59
     creating
    0.58
     setting
    0.56
     making
    0.54
    Activations Density 0.002%

    No Known Activations