© 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. 43610
    Prev
    Next
    INDEX
    Explanations

    sticking/adhering

    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
     pobres
    -0.57
    cs
    -0.57
    ness
    -0.56
    s
    -0.54
     blancas
    -0.54
     pauvres
    -0.53
    note
    -0.50
    ses
    -0.49
    psi
    -0.49
     religión
    -0.48
    POSITIVE LOGITS
    antd
    0.80
    ChildScrollView
    0.79
     doInBackground
    0.76
    __":
    0.72
    \{\\
    0.70
    DockStyle
    0.70
     JpaRepository
    0.67
    tableFuture
    0.66
    WebElementEntity
    0.65
    AlterField
    0.64
    Activations Density 0.074%

    No Known Activations