© 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. 4-CLT-HP
    7. 4551
    Prev
    Next
    INDEX
    Explanations

    correct

    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
     and
    -0.52
     common
    -0.47
     natural
    -0.46
    ,
    -0.45
     free
    -0.44
    unknownFields
    -0.44
     or
    -0.44
    mel
    -0.43
     normal
    -0.43
     results
    -0.43
    POSITIVE LOGITS
    AnchorStyles
    0.80
     تضيفلها
    0.80
    httphttps
    0.79
    脚注の使い方
    0.78
    #+#
    0.76
     שוליים
    0.72
    Jeografia
    0.71
    省市镇
    0.71
    adget
    0.71
    rrggbb
    0.71
    Activations Density 0.001%

    No Known Activations