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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12826
    Prev
    Next
    INDEX
    Explanations

    dispersed

    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
    IndentedString
    -0.67
    Cyfeiriadau
    -0.64
    +#+#
    -0.55
     متعلقه
    -0.53
    )]);
    -0.53
    viewDidLoad
    -0.53
     detaine
    -0.53
    Географиясе
    -0.52
    fjspx
    -0.52
     endwhile
    -0.52
    POSITIVE LOGITS
     Existence
    0.68
     Ranking
    0.62
    featureID
    0.60
     Presence
    0.58
    pend
    0.54
     Result
    0.54
    ate
    0.53
    stood
    0.52
     Searching
    0.52
    ed
    0.51
    Activations Density 0.052%

    No Known Activations