© 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. 1-CLT-HP
    7. 12175
    Prev
    Next
    INDEX
    Explanations

    ownership/responsibility

    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
    MessageTagHelper
    -0.79
    Tembelea
    -0.71
    ponses
    -0.71
     snippetHide
    -0.69
    Ligações
    -0.69
    GEBURTSDATUM
    -0.68
    makeText
    -0.67
     Roskov
    -0.67
    ]--;
    -0.66
    createCanvas
    -0.65
    POSITIVE LOGITS
     autorytatywna
    0.43
     बजाय
    0.41
     principaux
    0.40
     comptes
    0.38
    bindParam
    0.37
     claim
    0.37
     universitarios
    0.37
    forRoot
    0.36
     kinderen
    0.36
     peruan
    0.36
    Activations Density 0.028%

    No Known Activations