© 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. 1018
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
    SizeF
    -0.91
    ftagPool
    -0.74
    antMatchers
    -0.73
    Geographie
    -0.70
    MemoryWarning
    -0.70
    afficheront
    -0.70
     CreateTagHelper
    -0.69
    styleType
    -0.69
    EndProject
    -0.68
     conceding
    -0.68
    POSITIVE LOGITS
     high
    0.40
    l
    0.39
    u
    0.37
    ↵
    0.37
    )}^{
    0.36
     säll
    0.36
    lim
    0.36
    sw
    0.36
     w
    0.35
    n
    0.35
    Activations Density 0.057%

    No Known Activations