© 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. 92948
    Prev
    Next
    INDEX
    Explanations

    daily

    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
     waschen
    -0.46
    oldest
    -0.46
    rasz
    -0.46
    彼らは
    -0.45
    jakan
    -0.45
    AndEndTag
    -0.44
     Savage
    -0.43
    च्छ
    -0.43
    ämä
    -0.43
    AddTagHelper
    -0.43
    POSITIVE LOGITS
    WaitGroup
    0.63
     uintptr
    0.62
    mobileqq
    0.60
     StatelessWidget
    0.59
     useStyles
    0.57
    sizeCache
    0.57
     invokingState
    0.54
    ้ม
    0.53
    englanniksi
    0.52
    addCell
    0.51
    Activations Density 0.000%

    No Known Activations