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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41743
    Prev
    Next
    INDEX
    Explanations

    Code and technical documentation

    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
    <eos>
    -0.66
     their
    -0.65
    -
    -0.64
    ↵↵
    -0.63
    /
    -0.51
     di
    -0.50
     our
    -0.50
    deleteById
    -0.49
    تر
    -0.49
     /
    -0.47
    POSITIVE LOGITS
    Personendaten
    1.21
     Monfieur
    1.05
     itſelf
    1.03
    ſelf
    1.02
     pleaſure
    1.02
     myſelf
    0.98
     Anſ
    0.97
     Jefus
    0.96
    IsMutable
    0.94
     Efq
    0.94
    Activations Density 1.714%

    No Known Activations