© 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. 5-CLT-HP
    7. 94062
    Prev
    Next
    INDEX
    Explanations

    mind

    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
    rungsseite
    -0.89
    <bos>
    -0.84
    Personendaten
    -0.79
     itſelf
    -0.71
    ]")]
    -0.71
    Vanjske
    -0.70
    matically
    -0.69
     AssemblyCulture
    -0.68
     disambiguazione
    -0.67
    MessageOf
    -0.67
    POSITIVE LOGITS
     also
    0.54
    essoas
    0.50
     I
    0.50
     this
    0.47
     now
    0.45
     PyTuple
    0.41
    これで
    0.41
     essentiels
    0.39
     innan
    0.38
     också
    0.38
    Activations Density 0.003%

    No Known Activations