© 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. 38918
    Prev
    Next
    INDEX
    Explanations

    "ier" suffix

    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
    ier
    -1.11
     characteristics
    -0.84
    IER
    -0.80
    ieren
    -0.68
     Characteristics
    -0.65
    GIH
    -0.60
    iero
    -0.53
    Characteristics
    -0.53
    resse
    -0.51
     attributes
    -0.50
    POSITIVE LOGITS
    aarrggbb
    0.81
     utafitiHapana
    0.73
    lesias
    0.60
    extAlignment
    0.60
    abstractmethod
    0.58
     OFDb
    0.58
    BOA
    0.57
    XmlAccessType
    0.56
    mored
    0.55
     összefoglaló
    0.54
    Activations Density 0.154%

    No Known Activations