© 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. 95114
    Prev
    Next
    INDEX
    Explanations

    explanations and problem-solving

    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
     jsPsych
    -0.72
     hvid
    -0.62
    sidemargin
    -0.58
     hvilken
    -0.56
     hvit
    -0.54
    ⓧ
    -0.53
     personaggi
    -0.52
     why
    -0.52
     how
    -0.52
     سكانية
    -0.52
    POSITIVE LOGITS
     scientifically
    0.56
     bib
    0.54
     musically
    0.54
    Harp
    0.53
     numerically
    0.52
     intellectually
    0.51
     lingu
    0.50
     FURTHER
    0.49
    AutoresizingMask
    0.47
     critically
    0.47
    Activations Density 0.000%

    No Known Activations