© 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. 4-CLT-HP
    4. 3468
    Prev
    Next
    INDEX
    Explanations

    ages of children

    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
     EconPapers
    -0.59
     marshes
    -0.54
    flasche
    -0.54
     évidence
    -0.53
    ManagedBean
    -0.52
     Schmerz
    -0.52
    Források
    -0.52
    Externé
    -0.51
    variates
    -0.50
    strokeColor
    -0.50
    POSITIVE LOGITS
     zero
    0.52
     zéro
    0.48
    webElement
    0.47
    ########.
    0.47
     over
    0.47
     below
    0.45
     under
    0.44
    ربای
    0.44
     eig
    0.44
    цезда
    0.44
    Activations Density 0.004%

    No Known Activations