© 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. 40055
    Prev
    Next
    INDEX
    Explanations

    atrix

    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
     myſelf
    -1.10
     purpoſe
    -1.09
     Efq
    -1.09
     Majefty
    -1.07
     mijne
    -1.07
     auroit
    -1.06
    __*/
    -1.05
     avoient
    -1.04
     Monfieur
    -1.04
     Diretto
    -1.02
    POSITIVE LOGITS
    s
    1.17
    som
    0.83
    sur
    0.80
     tr
    0.71
    en
    0.71
     o
    0.70
    ت
    0.70
    sho
    0.70
    sv
    0.69
    spo
    0.69
    Activations Density 0.074%

    No Known Activations