© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13596
    Prev
    Next
    INDEX
    Explanations

    and

    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
     ;
    -0.51
     rei
    -0.47
     those
    -0.45
     Mil
    -0.44
     co
    -0.43
     a
    -0.43
     el
    -0.43
     Finley
    -0.43
     Fior
    -0.42
    ss
    -0.42
    POSITIVE LOGITS
    Geplaatst
    0.96
    HtmlAttribute
    0.93
    Personendaten
    0.84
    BufferException
    0.75
     pouvoit
    0.73
     auroit
    0.73
     quæ
    0.72
     lumineuse
    0.71
     useRouter
    0.69
    IsContent
    0.68
    Activations Density 0.052%

    No Known Activations