© 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. 5-CLT-HP
    7. 96280
    Prev
    Next
    INDEX
    Explanations

    past tense/passive voice words

    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
    v
    -0.52
    ​
    -0.40
    ​​
    -0.39
    ly
    -0.38
    ↵↵
    -0.37
    #
    -0.37
    á
    -0.37
    IGEN
    -0.36
     
    -0.35
    #
    -0.34
    POSITIVE LOGITS
    +#+#
    1.52
     disambiguazione
    1.51
    GEBURTSDATUM
    1.37
    ніципалі
    1.32
    featureID
    1.23
     AssemblyCulture
    1.20
     ModelExpression
    1.16
     Roskov
    1.16
     propOrder
    1.16
    LookAnd
    1.13
    Activations Density 0.098%

    No Known Activations