© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45597
    Prev
    Next
    INDEX
    Explanations

    plants

    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
    <bos>
    -0.79
     Monfieur
    -0.75
     صوتيه
    -0.74
    EndGlobalSection
    -0.66
     المعيارى
    -0.66
    ftagPool
    -0.65
     Eſ
    -0.62
    Rhestr
    -0.60
     referenties
    -0.59
    mtliche
    -0.59
    POSITIVE LOGITS
    consulté
    0.51
     سكانية
    0.50
    htë
    0.50
    AddTagHelper
    0.46
    fhir
    0.45
    CodedInputStream
    0.45
    τός
    0.44
    heroku
    0.44
    ondre
    0.43
    poo
    0.42
    Activations Density 0.011%

    No Known Activations