© 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. 20-CLT-HP
    7. 73548
    Prev
    Next
    INDEX
    Explanations

    _

    np_max-act-logits · 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
    debut
    -1.20
    launch
    -1.20
     debut
    -1.16
     debuts
    -1.16
    Launching
    -1.13
     launching
    -1.13
     Launching
    -1.13
    beginning
    -1.11
     launch
    -1.09
    Debut
    -1.09
    POSITIVE LOGITS
    enumi
    0.51
    ิน
    0.36
    ณี
    0.34
     participante
    0.32
    ян
    0.31
    sive
    0.29
    бам
    0.29
    ô
    0.29
    бе
    0.28
     applic
    0.28
    Activations Density 0.000%

    No Known Activations