© 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. 0-CLT-HP
    4. 97568
    Prev
    Next
    INDEX
    Explanations

    to

    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
    ignez
    -0.61
     Mean
    -0.58
    dfunding
    -0.58
    have
    -0.58
    }))
    
    -0.57
    Have
    -0.56
     saites
    -0.56
     Have
    -0.55
    ")){
    -0.55
     zuständig
    -0.55
    POSITIVE LOGITS
    PyTuple
    0.62
     AssemblyCulture
    0.61
     be
    0.60
     help
    0.57
     extract
    0.56
     construct
    0.56
    Bioaccumulative
    0.55
     which
    0.53
    protoimpl
    0.53
     withstand
    0.52
    Activations Density 0.108%

    No Known Activations