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. 0-CLT-HP
    4. 40880
    Prev
    Next
    INDEX
    Explanations

    Document excerpts

    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
    ViewFeatures
    -0.83
     snippetHide
    -0.60
     endfor
    -0.58
    ########.
    -0.57
    Бахар
    -0.56
    RequiresApi
    -0.53
     Autorizaciones
    -0.52
     собою
    -0.52
    seteq
    -0.52
    |}{}
    -0.52
    POSITIVE LOGITS
     يتيمه
    0.63
     propOrder
    0.63
     AppCompatTheme
    0.52
    Ost
    0.51
    East
    0.51
     Ceux
    0.51
    izie
    0.51
     Northeast
    0.50
    yfik
    0.50
    ρύ
    0.50
    Activations Density 1.590%

    No Known Activations