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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5148
    Prev
    Next
    INDEX
    Explanations

    Accessing something

    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
     IconData
    -0.50
     <=",
    -0.48
    MessageTagHelper
    -0.47
    viewtopic
    -0.45
    DETECT
    -0.44
    itag
    -0.43
    号
    -0.42
    kunjung
    -0.42
    EnableWeb
    -0.41
    IsInitialized
    -0.41
    POSITIVE LOGITS
     this
    0.64
    MENAFN
    0.58
    astien
    0.57
    Geplaatst
    0.56
    зулта
    0.54
    "{\
    0.52
     '\\;'
    0.52
    urbing
    0.50
     please
    0.50
    Karriere
    0.50
    Activations Density 0.000%

    No Known Activations