© 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. 5-CLT-HP
    7. 1178
    Prev
    Next
    INDEX
    Explanations

    similar to

    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
    hnia
    -0.52
    <bos>
    -0.49
    Хьажоргаш
    -0.47
     Contain
    -0.47
     JADX
    -0.47
    پیوند
    -0.46
    tersebut
    -0.46
     Transplantation
    -0.46
    titleMargin
    -0.45
    gether
    -0.45
    POSITIVE LOGITS
    ,
    0.69
    GEBURTSDATUM
    0.59
     "...
    0.58
     “…
    0.55
     "[
    0.54
     dAtA
    0.54
     “...
    0.53
    EndInit
    0.52
    、「
    0.52
     where
    0.51
    Activations Density 0.001%

    No Known Activations