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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97138
    Prev
    Next
    INDEX
    Explanations

    WO

    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
     Ba
    -1.00
    WO
    -0.80
    Ba
    -0.72
    OF
    -0.67
    featureID
    -0.66
     WO
    -0.65
     betweenstory
    -0.65
     ba
    -0.64
     تضيفلها
    -0.63
    LabelTagHelper
    -0.58
    POSITIVE LOGITS
     Unido
    0.48
    StoreMessageInfo
    0.46
    stab
    0.45
    zaj
    0.44
    lo
    0.43
    si
    0.42
    ctive
    0.42
     immunos
    0.42
    NgModule
    0.41
     dusting
    0.41
    Activations Density 0.053%

    No Known Activations