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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 45724
    Prev
    Next
    INDEX
    Explanations

    Common/filler words

    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
    IntoConstraints
    -0.71
    AddTagHelper
    -0.60
    fromnode
    -0.56
    ingress
    -0.56
    phylococcus
    -0.55
    sizeCache
    -0.54
    theless
    -0.53
    etheless
    -0.53
     leetcode
    -0.53
    '][$
    -0.52
    POSITIVE LOGITS
     quelcon
    0.56
     normaux
    0.52
     refroid
    0.48
     ordinaires
    0.47
    maic
    0.47
     réfrig
    0.47
     craindre
    0.47
     fasse
    0.47
     fidèles
    0.44
     religieuses
    0.43
    Activations Density 0.011%

    No Known Activations