© 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. 971
    Prev
    Next
    INDEX
    Explanations

    forum posts

    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
     me
    -0.80
    me
    -0.59
     Me
    -0.54
    if
    -0.51
     my
    -0.49
    <bos>
    -0.49
    Me
    -0.49
     If
    -0.48
     conmigo
    -0.48
     is
    -0.47
    POSITIVE LOGITS
    Portály
    0.88
     jScrollPane
    0.83
     विश्वसनीयता
    0.81
    WindowConstants
    0.78
     autorytatywna
    0.71
     незавершена
    0.69
    Hochspringen
    0.68
    +#+
    0.68
     Walkover
    0.66
    AxisAlignment
    0.66
    Activations Density 0.011%

    No Known Activations