© 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. 20-CLT-HP
    7. 74662
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act-logits · 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
    ########.
    -0.69
     AssemblyCompany
    -0.67
     esternos
    -0.66
     defaultstate
    -0.65
    XmlAccessType
    -0.62
     jsPsych
    -0.61
    HasAnnotation
    -0.59
    MessageTagHelper
    -0.58
    InputTagHelper
    -0.58
    الحياه
    -0.57
    POSITIVE LOGITS
    SequentialGroup
    0.50
    Saint
    0.46
     Saint
    0.46
     SAINT
    0.45
     Licence
    0.45
    SAINT
    0.41
    TSP
    0.40
     forKey
    0.40
    anez
    0.40
     Clipboard
    0.40
    Activations Density 0.010%

    No Known Activations