© 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. 1137
    Prev
    Next
    INDEX
    Explanations

    starting, marriage, promotions

    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
    LookAnd
    -0.87
    httphttps
    -0.71
    rush
    -0.68
    ContentAsync
    -0.66
    发表于
    -0.64
     snippetHide
    -0.63
    Hentet
    -0.63
     protoimpl
    -0.59
     resourceCulture
    -0.58
     autorytatywna
    -0.57
    POSITIVE LOGITS
    er
    0.60
    ölkerung
    0.53
     backed
    0.51
    .(*
    0.51
    cold
    0.51
    aula
    0.50
    voll
    0.49
     principal
    0.49
     Comprehension
    0.47
    age
    0.47
    Activations Density 0.064%

    No Known Activations