© 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. 0-CLT-HP
    7. 91993
    Prev
    Next
    INDEX
    Explanations

    superseded

    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
     Estes
    -1.12
    PreferredItem
    -1.03
     initComponents
    -0.84
     superseded
    -0.84
     Norma
    -0.80
    orphism
    -0.80
     AssemblyCulture
    -0.76
    enderror
    -0.75
    Norma
    -0.73
    yce
    -0.73
    POSITIVE LOGITS
     kec
    0.49
    biamo
    0.45
    gether
    0.42
     cử
    0.42
     N
    0.41
     together
    0.41
     Kam
    0.40
    jetbrains
    0.40
    epam
    0.40
    ppert
    0.40
    Activations Density 1.687%

    No Known Activations