© 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. 0-CLT-HP
    7. 93345
    Prev
    Next
    INDEX
    Explanations

    going

    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
     going
    -0.93
    going
    -0.81
    Going
    -0.71
    coming
    -0.62
     doubtnut
    -0.61
     GOING
    -0.60
     depositphotos
    -0.60
     imagining
    -0.57
    DoubleQuotes
    -0.57
     Going
    -0.57
    POSITIVE LOGITS
    曖昧さ回避
    0.60
     back
    0.53
    Clik
    0.51
     Архивировано
    0.51
    $__
    0.50
     Signalez
    0.49
    zonego
    0.48
     >::
    0.47
    czegó
    0.47
    ]}"
    0.46
    Activations Density 0.027%

    No Known Activations