© 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. 4-CLT-HP
    7. 1640
    Prev
    Next
    INDEX
    Explanations

    configuration data

    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
    WriteBarrier
    -0.60
    ObjectContext
    -0.55
    ghen
    -0.52
     kredit
    -0.52
     righe
    -0.52
    atric
    -0.52
    carbonyl
    -0.51
    ATURE
    -0.50
    ViewGroup
    -0.50
    ftime
    -0.50
    POSITIVE LOGITS
    ars
    0.64
    DockStyle
    0.62
    __(/*!
    0.61
    bkz
    0.56
    arsh
    0.53
     useRouter
    0.52
    ARS
    0.49
     ISNI
    0.49
     noDo
    0.47
     Daria
    0.47
    Activations Density 0.001%

    No Known Activations