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. 11141
    Prev
    Next
    INDEX
    Explanations

    technical documents and code

    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
    magnitude
    -1.12
    RenderAtEndOf
    -0.70
    anting
    -0.66
    ंदीखरीदारी
    -0.66
     Administrativna
    -0.65
     ProtoMessage
    -0.65
     فريبيس
    -0.64
    toThrow
    -0.63
     CascadeType
    -0.62
     OnEnable
    -0.61
    POSITIVE LOGITS
    AddTagHelper
    0.51
    });*/
    0.47
     catch
    0.46
    erf
    0.46
    catch
    0.46
    }*/
    
    0.45
     dx
    0.45
    uría
    0.44
    ұ
    0.44
     LUMP
    0.43
    Activations Density 0.008%

    No Known Activations