Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74224
    Prev
    Next
    INDEX
    Explanations

    technical/research text

    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
    MLLoader
    -0.61
     bezeichneter
    -0.57
    Бахар
    -0.52
    ɕ
    -0.51
    Personendaten
    -0.51
    ChildScrollView
    -0.50
    posedge
    -0.49
    `;
    
    -0.49
    ivasan
    -0.47
    bekah
    -0.46
    POSITIVE LOGITS
    AndEndTag
    0.73
     DAC
    0.57
     DCC
    0.56
     MOP
    0.53
    Données
    0.53
     drowsiness
    0.53
    euse
    0.52
     ECE
    0.52
     dbl
    0.52
    DAC
    0.51
    Activations Density 0.012%

    No Known Activations