© 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. 2226
    Prev
    Next
    INDEX
    Explanations

    Building floors/locations

    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
    <?
    -0.70
    igrette
    -0.56
     BIBSYS
    -0.53
    
    -0.53
    SafeMath
    -0.53
    pany
    -0.51
    netje
    -0.51
    hammad
    -0.51
    ietf
    -0.50
    ğından
    -0.50
    POSITIVE LOGITS
     '\\;'
    0.53
    +#+#
    0.52
    AddTagHelper
    0.50
    FunctionFlags
    0.49
     postIndex
    0.48
     viewType
    0.46
     kaynağından
    0.45
    aarrggbb
    0.45
     sanitaires
    0.44
    InSection
    0.44
    Activations Density 0.001%

    No Known Activations