© 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. 94978
    Prev
    Next
    INDEX
    Explanations

    technical documentation

    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
    ніципалі
    -0.96
    Datuak
    -0.89
     незавершена
    -0.86
     kasarigan
    -0.83
    Personendaten
    -0.83
     invokingState
    -0.82
    ⓧ
    -0.81
    twimg
    -0.76
    adaptiveStyles
    -0.75
    enumi
    -0.75
    POSITIVE LOGITS
     pleaſure
    0.54
    :
    0.50
     houſe
    0.50
     Efq
    0.48
    ^(@)
    0.44
     trick
    0.44
    ſelf
    0.43
    ((*
    0.42
     themſelves
    0.42
     Monfieur
    0.42
    Activations Density 0.001%

    No Known Activations