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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45137
    Prev
    Next
    INDEX
    Explanations

    ERT / special character tokens

    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
    ERT
    -1.30
    ert
    -0.49
     (
    -0.44
    ↵↵
    -0.43
     While
    -0.42
     Während
    -0.40
    ERTE
    -0.38
     We
    -0.37
    र्ट
    -0.36
     compensation
    -0.36
    POSITIVE LOGITS
    contentLoaded
    1.05
     nahilalakip
    0.99
     myſelf
    0.97
    TypedDataSet
    0.94
     createSlice
    0.88
    ]--;
    0.87
     Monfieur
    0.85
    FieldBuilder
    0.83
     Theſe
    0.82
     EconPapers
    0.81
    Activations Density 1.684%

    No Known Activations