© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 613
    Prev
    Next
    INDEX
    Explanations

    to

    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
     esternos
    -0.82
    StoryboardSegue
    -0.80
    ]")]
    -0.63
     Efq
    -0.57
    ratory
    -0.57
    pentry
    -0.55
     ")";
    -0.52
    oxys
    -0.52
    ſelf
    -0.52
    ographics
    -0.50
    POSITIVE LOGITS
    IVEREF
    0.58
     Waiting
    0.54
    DockStyle
    0.52
    îtra
    0.51
     conducta
    0.49
     Implement
    0.49
     address
    0.49
    ंदीखरीदारी
    0.48
     ویکی‌پدیا
    0.48
     implement
    0.48
    Activations Density 0.002%

    No Known Activations