Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 1651
    Prev
    Next
    INDEX
    Explanations

    math questions

    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
    rvats
    -0.54
    AddTagHelper
    -0.54
    psilon
    -0.54
    ignty
    -0.54
    +='
    -0.52
     awakeFromNib
    -0.52
    ]='\
    -0.50
    ellery
    -0.49
    vericks
    -0.49
    MIDDLEWARE
    -0.48
    POSITIVE LOGITS
    :
    0.73
     blessé
    0.59
    $:
    0.59
    :$
    0.57
    findpost
    0.55
    here
    0.54
    no
    0.54
     écrits
    0.53
    :}
    0.53
     varandra
    0.53
    Activations Density 0.068%

    No Known Activations