© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1969
    Prev
    Next
    INDEX
    Explanations

    Time periods, especially years

    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
     @"/
    -0.57
    ESSIONS
    -0.56
    IUS
    -0.55
     Sixty
    -0.53
    elesai
    -0.53
    onii
    -0.53
     veli
    -0.53
     Number
    -0.52
     Branches
    -0.52
     courses
    -0.51
    POSITIVE LOGITS
    Geplaatst
    0.61
    DJANGO
    0.59
     reír
    0.58
    rungsseite
    0.57
    siger
    0.57
    RTCF
    0.55
    曖昧さ回避
    0.51
     muerto
    0.50
    Aktualisiert
    0.50
    <bos>
    0.49
    Activations Density 0.133%

    No Known Activations