© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1
    Prev
    Next
    INDEX
    Explanations

    hacking, breaking

    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
    Enllaces
    -0.49
    tania
    -0.46
     esternos
    -0.44
     bel
    -0.41
    Rujuakan
    -0.41
     skall
    -0.40
     Kort
    -0.40
    isantes
    -0.40
    Imag
    -0.40
    ping
    -0.40
    POSITIVE LOGITS
     NSCoder
    0.84
    Хьажоргаш
    0.64
     uLocal
    0.61
     للاسماء
    0.61
     into
    0.61
     down
    0.59
    enschappelijke
    0.59
    ]")]
    0.59
    ądź
    0.58
    dumps
    0.58
    Activations Density 0.000%

    No Known Activations