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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3251
    Prev
    Next
    INDEX
    Explanations

    general text

    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
     виправивши
    -0.73
    wegg
    -0.63
     يتيمه
    -0.63
    SourceChecksum
    -0.63
    oa̍t
    -0.62
    Personendaten
    -0.61
    ագրություններ
    -0.61
     betweenstory
    -0.60
    EndGlobalSection
    -0.60
    salms
    -0.58
    POSITIVE LOGITS
    ByExample
    0.47
    éb
    0.43
    Stat
    0.43
     intptr
    0.41
    MatInputModule
    0.41
    nment
    0.41
     lk
    0.41
     brought
    0.41
     current
    0.40
     szem
    0.40
    Activations Density 0.001%

    No Known Activations