© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93532
    Prev
    Next
    INDEX
    Explanations

    introduction

    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
     of
    -0.80
    vsk
    -0.47
    e
    -0.45
     veille
    -0.42
    Introduce
    -0.42
    cs
    -0.41
    元年
    -0.41
     Vibration
    -0.40
     Introduce
    -0.40
    öm
    -0.40
    POSITIVE LOGITS
    ValueStyle
    0.89
    AnchorStyles
    0.75
    featureID
    0.72
    WithIOException
    0.70
    enderror
    0.66
    MediaStore
    0.63
    welijk
    0.63
     HasFactory
    0.61
    TagHelper
    0.59
    afone
    0.59
    Activations Density 0.017%

    No Known Activations