© 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. 45800
    Prev
    Next
    INDEX
    Explanations

    ump

    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
    SequentialGroup
    -0.59
    noaa
    -0.57
     layui
    -0.56
     LoggerFactory
    -0.55
    évaluateur
    -0.54
    IService
    -0.52
    Commissioner
    -0.52
    KERNEL
    -0.50
     embeddings
    -0.50
    Demografía
    -0.50
    POSITIVE LOGITS
    tanleria
    0.58
    tagHelperRunner
    0.54
    sistors
    0.51
    gestellt
    0.49
     Administrativna
    0.48
     Numerade
    0.47
    ælp
    0.47
    éenne
    0.47
    ALF
    0.46
    AddTagHelper
    0.46
    Activations Density 0.023%

    No Known Activations