© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97136
    Prev
    Next
    INDEX
    Explanations

    kept

    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
     AssemblyCulture
    -0.93
     виправивши
    -0.87
    tonsoft
    -0.86
     tartalomajánló
    -0.85
    IntoConstraints
    -0.84
    kháu
    -0.78
     doubtnut
    -0.77
    CppMethod
    -0.75
     betweenstory
    -0.75
    Portale
    -0.75
    POSITIVE LOGITS
     us
    0.86
     the
    0.83
     them
    0.76
     a
    0.74
     it
    0.74
     her
    0.73
     this
    0.71
     an
    0.71
     me
    0.65
     many
    0.65
    Activations Density 0.014%

    No Known Activations