© 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. 0-CLT-HP
    7. 91032
    Prev
    Next
    INDEX
    Explanations

    luck

    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
    كويكب
    -0.57
    むしろ
    -0.57
    greenrobot
    -0.55
    "]:
    -0.54
     CreateTagHelper
    -0.54
     насељу
    -0.53
    "}")
    -0.53
    : 
    -0.50
    zzard
    -0.50
    "]]
    -0.50
    POSITIVE LOGITS
     morire
    0.58
     rosse
    0.57
    #
    0.55
    SourceChecksum
    0.54
    MessageOf
    0.53
     fusca
    0.51
    참고
    0.50
    /*
    0.49
     sportiva
    0.48
    บค
    0.48
    Activations Density 0.934%

    No Known Activations