© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42915
    Prev
    Next
    INDEX
    Explanations

    subsequent

    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
     later
    -2.03
     afterwards
    -1.89
     subsequently
    -1.88
     afterward
    -1.79
     subsequent
    -1.76
    later
    -1.74
    Later
    -1.72
    Afterwards
    -1.69
     posteriormente
    -1.68
     Subsequently
    -1.66
    POSITIVE LOGITS
     silken
    0.63
     beginnetje
    0.60
    ity
    0.57
     examples
    0.56
     Muses
    0.56
     dozen
    0.55
     astral
    0.55
     glories
    0.55
    ränkt
    0.55
     moderation
    0.54
    Activations Density 0.057%

    No Known Activations