© 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. 2748
    Prev
    Next
    INDEX
    Explanations

    faith/belief

    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
     kanyang
    -0.51
    ształ
    -0.50
    Xna
    -0.48
    kena
    -0.48
     Reverso
    -0.46
    onatos
    -0.45
    Jornal
    -0.45
     ensemble
    -0.44
    collate
    -0.44
    PEAT
    -0.44
    POSITIVE LOGITS
    Personendaten
    0.71
    MigrationBuilder
    0.61
    initComponents
    0.57
    walker
    0.56
    mergeFrom
    0.54
    MockMvc
    0.52
    AutoScale
    0.51
     Quij
    0.51
    GOTREF
    0.50
    ManagedBean
    0.49
    Activations Density 0.001%

    No Known Activations