© 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. 45584
    Prev
    Next
    INDEX
    Explanations

    soft

    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
    رشف
    -0.57
    <bos>
    -0.57
     ['$
    -0.57
    ContentAsync
    -0.55
    soft
    -0.55
     Soft
    -0.54
    tagHelper
    -0.54
     soft
    -0.53
    Soft
    -0.53
    AddColumn
    -0.50
    POSITIVE LOGITS
     BoxDecoration
    0.73
    omitempty
    0.57
     intest
    0.50
     discontinuous
    0.50
     nahilalakip
    0.50
    月号
    0.48
    uan
    0.47
    stm
    0.47
    retta
    0.45
    angliski
    0.45
    Activations Density 0.105%

    No Known Activations