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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11442
    Prev
    Next
    INDEX
    Explanations

    mentions of "time"

    oai_token-act-pair · gemini-2.0-flash

    words related to time or temporal references

    np_token-act-pair-logits · gpt-4o-mini

    Time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.52
    Enllaces
    -0.44
    يديا
    -0.39
     geliefert
    -0.38
    simus
    -0.37
    談社
    -0.37
    bulo
    -0.36
     pagamento
    -0.36
    bium
    -0.36
     Walkover
    -0.36
    POSITIVE LOGITS
    principalColumn
    0.79
     resourceCulture
    0.79
    InjectAttribute
    0.73
    حوالہ
    0.70
    PhysRev
    0.69
    Geplaatst
    0.69
    出版年
    0.68
    Дереккөздер
    0.68
    contentLoaded
    0.67
    protoimpl
    0.67
    Activations Density 0.173%

    No Known Activations